SlideShare une entreprise Scribd logo
1  sur  6
Télécharger pour lire hors ligne
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3569
Terrorism Analysis through Social Media using Data Mining
Shamika Karnik1, Sonal Singh2, Sahithi Shetty3, Sujata Kullur4
1,2,3 Student, Dept. of Information Technology, Usha Mittal Institute of Technology, Maharashtra, India
4 Professor, Dept. of Information Technology, Usha Mittal Institute of Technology, Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - There has been a tremendous increase in
internet usage in the following decade which leads to many
great ideas and technologies emerging. But as they say
“with good comes bad”. So, a lot of malicious activity is also
noticed which has been done by unknown groups. Groups
can be labelled as fraudster group, terror groups and many
other unethical groups. Groups use this social media
platform for extracting information, and this piece of
information is used by them to expand terrorist activities.
This has resulted as a growing activity over the past
decades. The basic idea behind this is to put an end to such
kind of activities or curb this activity through technology.
This paper introduces various deep learning approaches
applied to the task of classifying terrorism through toxicity
in online comments. Out of which the impact of Deep Neural
Network(DNN), Convolutional Neural Networks (CNN),
together with word and character-level embeddings, on
identifying toxicity in text is implemented. The aim is to
provide both the models DNN and CNN because of their
capability to provide appropriate results with the help of
technical analysis of the data set. The objective is to
compare both the models and use the best one suited when
it comes to a particular company data set. The results
obtained show that the individual models work well when
the data provided suits the model and appropriate
parameter values are set. The accuracy of the models for
each attribute is over 90%. Both the models can prove to be
an asset to social media users. Thus, the paper presented
provides models which can predict the percentage of a
particular tweet and classify it into 6 labels: toxicity, severe
toxicity, obscenity, threat, insult or identity hate.
Key Words: Social media, Terrorist activities, Deep
Neural Network, Convolutional Neural Network, Deep
Learning, GUI.
1. INTRODUCTION
Terror teams use social media as a medium to extract data
and recruit’s violence within the society. Social media
operate through world platforms with open access that
leave digital signatures for enforcement agencies to track
them down. Successful operations to curb malicious
activities and track those accountable are performed with
the assistance of open- source data. By acting smoothly on
this obtainable data, it conjointly becomes attainable to
prevent incidents before they occur. Terrorist
organisations operate in such a way that the social
networks ought to be able to give the primary pur- pose of
contact with potential candidates for accomplishment.
Once initial contact is established additional
communication is shifted to associate encrypted channels
wherever tracking becomes nearly impossible, which is
further complicated by privacy and protection laws
prevalent in various countries around the world.
Conversational toxicity is a difficulty that may lead people
both to prevent genuinely expressing them- selves and to
prevent seeking others’ opinions out of fear of
abuse/harassment. The goal of this project is to use deep
learning to spot terrorism through toxicity in text, which
can be accustomed to help deter users from posting
potentially hurtful messages, craft more civil arguments
when engaging in discourse with others, and to determine
the toxicity of other users’ comments.
This project aims to implement various deep learning
mod- els - specifically multilayer perceptron (MLP),Deep
Neural Networks(DNN) and Convolutional Neural
Networks (CNN) - to tackle the above task, assessing these
models’ performances on both binary and multi-label
classification tasks. Our project also studies the
applications of those models at both word-level and
character-level granularities.
2. REVIEW OF LITERATURE
The basis of study idea: The fastest growing area within
the research is web data processing. It consists of web
data processing, web structure mining, and website
mining. Web data mining is that the process of discovering
the users accessing pattern from the online data logs. the
net structure mining is helpful in discovering the
knowledge from the structure of the hyperlinks. The Paper
presented by George Kalpakis, Theodora Tsikrika,
Stefanos Vrochidis and Ioannis Kompat- siaris their have
examine a social media network consisting of terrorism
related Twitter accounts. Our data were collected through
asocial media discovery tool executing queries on the
Twitter API (https://dev.twitter.com/) employing a set of
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3570
Arabic keywords associated with terrorists’ propaganda.
and next their examine which centrality measure is in a
position to detect the foremost influential Twitter user(s)
and limit the communication effectively within the
terrorist network.(1) The paper presented by Taiwo
Kolajo, Olawande Daramola is to present how big data will
be accustomed prevent and combat terrorism in
developing countries. First, we present a bird-eye view of
the analytical procedure for handling Big Data for
terrorism detection, second, the architectural framework,
thereafter, an outline of key components of the
architecture and lastly, a use case scenario. during this
paper, a use case of Social Media Analysis for Combating
Terrorism (SMACT) Model was also presented so as to
demonstrate the plausibility of its implemen- tation to
resolve real security problems that relates to terrorism.(2)
The paper presented by Ali Alzahrani, Khalid Bashir
Bajwa, Turki Alghamdi and Hanaa Aldahawi their
presented the methods utilized by terrorists to spread
their messages using social media. it’s understood that
containing terrorism- related material on social media is
critical. We analysed the associated problems and
proposed strategies towards an answer for containment of
terrorism-related activities. The proposed strategy
includes the employment of linguistic communication
processing to create and expand a dataset by searching for
terrorist related data on social networks, the reduction of
the info using data sampling techniques, the employment
of information mining methods on reduced data to spot
the patterns and extract useful information and therefore
the use of social network analysis to uncover the
associations and relationship between individuals and
terrorist groups, their structure and their modes of
operations.(3) The Journal written by Aakash Negandhi,
Soham Gawas, Prem Bhatt, Priya Porwal during this the
system detects patterns and relevant information in texts
in websites using data processing. The web site will have
these characteristics: Load balancing, easy accessibility,
user friendly , efficient and reliable and simple
maintenance. This technique has used basic data
processing moreover as a web mining concept . They used
Visual Studio and Sql Server 2008 to make and record the
project.(4) The article written by J. Kiruba, P. Sumitha, K.
Monisha, S. Vaishnavi during this the system delivers
event notification which is employed to watch the
activities and delivers notification consistent with the
investigation knowledge. The monitored population is
unbalanced so the entire population of internet users is
really near low, that’s zero. it’s not expected that the
terrorists activities on the net to be a stable either-in. This
study demonstrates how to use search engines to
categorise websites into the categories of terrorism and
anti-terrorism.This study results the concepts and
methods to detect terrorists and their behaviour and their
supporters who supports for terror related activities in
society using an online access.(5) The journal written by
Mrs. T. Suvarna Kumari, Mr. Narsaiah Putta during this
framework will check website pages whether a page is
advancing fear based oppression. This framework will
characterize the web site pages into different classes and
kind them fittingly. There are two highlights utilized
during this framework that’s information mining and web
mining.
During this paper, the info pre-handling could be a
significant undertaking of TTUM application. Accordingly
web mining procedure will be utilized for distinguishing
and maintaining a strategic distance from fear dangers led
to by psychological oppressors everywhere throughout
the planet.(6)
3. METHODOLOGY
This paper aims to make the simplest model to predict and
analyze the epochs values for the Terrorism Analysis. The
paper presents two models CNN and DNN for the analysis
which can help the concerned officials to create a more
informed decision. The structure of the model presented is
as shown in figure below. The software framework is
made using python for the 2 algorithms of CNN and DNN.
3.1 Dataset
Cleaning and filtering of the data set is done to remove
duplicate records, normalize the values, accounting for
missing data and removing irrelevant data items. The
training data set is provided to the classifier as input. This
classified data is als used for the purpose of testing. The
system will operate mainly in two stages:
● Training phase
● Testing phase
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3571
Fig -1: Model Architecture
3.2 Training Phase
Training a model simply means learning (determining)
good values for all the weights and the bias from labeled
examples. The goal of training a model is to find a set of
weights and biases that have low loss, on average, across
all examples. Classification assumes labeled data: we know
how many classes there are, and for each class we have
examples (labeled data).
3.3 Convolutional Neural Network
Convolutional Neural Network is a class of deep neural
networks which is used in Computer Vision. A CNN
generally comprises three layers: a convolutional layer, a
pooling layer, and a totally connected layer.
3.3.1) Convolution Layer: The convolution layer is the core
building block of the CNN.It carries the most portion of the
network’s computational load. This layer conducts a real
between two matrices, one of which is a set of learnable
parameters referred to as a kernel, and the other is the
restricted region of the receptive field. The kernel is
smaller in size than a picture, but it has more depth. A
stride is the size of the kernel when it slides. If we consider
an input of size W x W x D and Dout number of kernels
with a spatial size of F with stride S and amount of
padding P, then the scale of output volume will be
calculated by the formula:Formula for Convolution Layer:
Wout = ((W − F + 2P )/S) + 1 (1)
It will give an output volume of size Wout x Wout x Dout.
3.3.2) Pooling Layer: The pooling layer is responsible for
replacing the network’s output at specific points by
calculating a summary statistic of neighboring outputs.
This minimizes the representation’s spatial size, which
reduces the amount of computation and weights required.
If we have an activation map of size W x W x D, a pooling
kernel of spatial size F, and stride S, then the scale of
output volume will be calculated by the subsequent
formula: Formula for Padding Layer:
Wout = ((W − F )/S) + 1 (2)
It will give an output volume of size Wout x Wout x D.
3.3.3) Fully Connected Layer: In this layer, neurons have
full connectivity with all other neurons within the
preceding and succeeding layer as seen in regular FCNN. A
matrix operation followed by a bias effect can be used to
calculate it. The FC layer aids in the mapping of
representations between the input and output.
Fig -2: CNN architecture for text classification,by
researchgate.net
3.4 Deep Neural Network
A deep neural network (DNN) is a synthetic neural
network with multiple layers between the input and
output layers.It is a set of neurons organized in a sequence
of multiple layers. Here,the neurons receive input from the
neuron activations from the previous layer, and perform
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3572
an easy computation for example we use a weighted sum
of the input followed by a nonlinear activation. The
neurons of this network jointly implement a posh
nonlinear mapping from the input to the output. This
mapping is learned from the information by adapt- ing the
weights of every neuron with the assistance of a way
called error backpropagation. A deep neural network
(DNN) will be considered as stacked neural networks, i.e.,
networks composed of several layers. FF-DNN, also called
multilayer perceptrons (MLP), are because the name
suggests DNNs where there’s quite one hidden layer and
therefore the network moves in barely forward direction
(no loopback). These neural networks are well-suited to
both classification and prediction. For spoken LID, we use
the classification approach. When the FF-DNN is employed
as a classifier, the input and output nodes will match the
input features and output classes. The most important
concepts in an exceedingly FF-DNN are weights, biases,
nonlinear activation and backpropagation. The input layer
has four elements which are I-1, I-2, I-3, and I-4. They
define an input, I = . What we want is to seek out one or
more patterns from the entities of the input, so those
patterns are accustomed to classify one output from the
opposite. so as to try and do that, we devise a variety of
hidden units with activation functions. Nonlinear
activation functions like Sigmoid, tanh, ReLU are
accustomed to form a pattern of active hidden units.
Let’s assume H-13, H-14, H-17, H-22, H-23, H-26,H-32, H-
33, H-36, and H-37 are needed for active output O-1. To
achieve this, we need to adjust the weights and biases in
such a way that these hidden nodes are activated by the
activation function. Firstly, the weights and biases are
randomly initialized. Later, we train this network with
tens of thousands of inputs. We make use of
backpropagation of error to adjust weights and biases, so
that the suitable values among them will activate the
hidden neurons. The set of weights and biases are called
feature sets or kernels., which will be used to uniquely
identify a particular output.(8)
Fig -3: Text classification using a multilayer deep neural
network architecture, via researchgate.net
3.5 Comparison between the two models
The two models were compared and supported the
methods employed for pre-processing, and processing the
info for predictions, the following table shows the
comparison between them.
Comparison Between CNN and DNN
Sr No. CNN DNN
1. Convolutional neural
networks (CNN) uses a
vari- ation of
multilayer percep-
trons and contains one
or more convolutional
layers that may be
either entirely
connected or pooled.
Deep Neural
Network (DNN) is
comparable to
artificial neural
networks and aims
to mimic the data
processing of the
brain.
2. In CNN rather than
weights we use kernels
that result in weight
sharing.
In DNN there’s no
Weight sharing.
3. CNN uses a
convolution operation
which represents a
selected filter.
DNN focuses more
on data from input
represented by a
bunch of non- linear
functions.
4. Consists of multiple
layers which are
convolutional layer,
pooling layer, fully
connected layer, and
nor- malising layer.
Consists of more
than 1 hidden layer.
5. When data flows
from input layer to
output layer, CNN
remembers the input
topology.
When data flows
from input layer to
output layer,DNN
forgets the input
topology.
6. Automatically detects
the important features
with no human
supervision.
Operating of neural
networks should be
trained under human
supervision.
Table -1: Comparison between the models
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3573
3.6 Testing Phase
Testing phase involves the prediction of unknown data
sample. The test set is a set of observations used to
evaluate the performance of the model using some
performance metric. It is important that no observations
from the training set are included in the test set.
4. RESULTS
Testing phase involves the prediction of unknown data
sample. The test set is a set of observations used to
evaluate the performance of the model using some
performance metric. It is important that no observations
from the training set are included in the test set.
4.1 DNN Model Results
It was observed that the number of epochs highly
impacted the accuracy of the model. Also, the model
performed well when a large dataset was included.
The accuracy using the DNN model was 97.21% .
Fig -4: Training and Validation accuracy by DNN model
Fig -5: Training and Validation loss by DNN model
4.2 CNN Model Results
The model was trained using 1D Convolutional Layer and
tested. The accuracy using CNN model was 97.64% .
Fig -6: Training and Validation accuracy by CNN model
Fig -7: Training and Validation loss by CNN model
5. CONCLUSIONS
Social media is said to be a trend nowadays which has
integrated technology, social interactions, construction of
words, pictures, videos and audios. It helps to induce
access to friends, tweets and user credentials. The method
of Extraction and Analysis is the challenging attribute in
Social Media because the data is dynamic and data is
unstructured in numerous sites. The project is principally
for the scholars to assist them in understanding the steps
of extracting content from different sites and are available
up with new advancement in developing applications by
using the active data. The info Mining practices and
algorithms is to develop different applications and help in
improving the status of the marketing field. This is often
our initial study which supplies basics about a way to start
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3574
with the applying development. Further studies are added
with improved algorithms and process of application
development. The proposed model is currently offline in
future work; it is extended for real-time Twitter data
streaming to predict further crimes. More crime classes
will be added to make the system efficient and robust.
ACKNOWLEDGEMENT
We have a great pleasure to express our gratitude to all
those who have contributed and motivated us during our
project work. We would like to express my special thanks
to our guide Prof. Sujata Kullur as well as our principal Dr.
Shikha Nema who gave gave us the golden opportunity to
do this wonderful project on the topic: Terrorism analysis
through social media using data mining, which also
helped us in doing a lot of Research and we came to know
about so many new things. We would also like to thank Dr.
Sanjay Shitole and Prof. Mohan Bonde for their valuable
inputs in completion of our project.
We are really thankful to them. Secondly we would also
like to thank our parents and friends who helped us a lot
in finalizing this project within the limited time frame.
REFERENCES
[1] Ilias Gialampoukidis, I., Kalpakis, G., Tsikrika, T.,
Vrochidis, S. & Kompatsiaris, I. (2016, August). Key player
identification in terrorism-related social media networks
using centrality measures. In 2016 European Intelligence
and Security Informatics Conference (EISIC) (pp. 112-
115).
[2] Taiwo Kolajo and Olawande Daramola. "Leveraging
big data to combat terrorism in developing countries." In
2017 Conference on Information Communication
Technology and Society (ICTAS), pp. 1-6. IEEE, 2017.
[3] Alzahrani, Ali, Khalid Bashir Bajwa, Turki Alghamdi,
and Hanaa Aldahawi. "Countering Terrorism on Social
Media Using Big Data." (2018): 35-42.
[4] Negandhi, Aakash, Soham Gawas, Prem Bhatt, and
Priya Porwal. "Detect Online Spread of Terrorism Using
Data Mining." IOSR Journal of Engineering (IOSRJEN) 17
(2016): 19.
[5] J. Kiruba, P. Sumitha, K. Monisha, S. Vaishnavi(2019),
“Enhanced Content Detection Method to Detect Online
Spread of Terrorism”.
[6] Mrs. T. Suvarna Kumari, Mr. Narsaiah Putta (2019),”
Web Data Mining to Detect Online Spread of Terrorism”.
[7] Sanskar Soni, Satyendra Singh Chouhan and Santosh
Singh Rathore (March 2022),”TextConvoNet:A
Convolutional Neural Network based Architecture for Text
Classification”.
[8] Shikha Jain, Ajit Kumar Jain and Shashi Pal Singh (Jan
2021),”A Multilayer Deep Learning Framework for Auto-
content Tagging”.

Contenu connexe

Similaire à Terrorism Analysis through Social Media using Data Mining

A SYSTEMATIC REVIEW ON MACHINE LEARNING INSIDER THREAT DETECTION MODELS, DATA...
A SYSTEMATIC REVIEW ON MACHINE LEARNING INSIDER THREAT DETECTION MODELS, DATA...A SYSTEMATIC REVIEW ON MACHINE LEARNING INSIDER THREAT DETECTION MODELS, DATA...
A SYSTEMATIC REVIEW ON MACHINE LEARNING INSIDER THREAT DETECTION MODELS, DATA...IJNSA Journal
 
Fake News Detection Using Machine Learning
Fake News Detection Using Machine LearningFake News Detection Using Machine Learning
Fake News Detection Using Machine LearningIRJET Journal
 
BINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNING
BINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNINGBINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNING
BINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNINGIRJET Journal
 
A REVIEW ON MACHINE LEARNING TECHNIQUES ON SOCIAL MEDIA DATA FOR POLICY MAKING
A REVIEW ON MACHINE LEARNING TECHNIQUES ON SOCIAL MEDIA DATA FOR POLICY MAKINGA REVIEW ON MACHINE LEARNING TECHNIQUES ON SOCIAL MEDIA DATA FOR POLICY MAKING
A REVIEW ON MACHINE LEARNING TECHNIQUES ON SOCIAL MEDIA DATA FOR POLICY MAKINGDeja Lewis
 
IDENTITY DISCLOSURE PROTECTION IN DYNAMIC NETWORKS USING K W – STRUCTURAL DIV...
IDENTITY DISCLOSURE PROTECTION IN DYNAMIC NETWORKS USING K W – STRUCTURAL DIV...IDENTITY DISCLOSURE PROTECTION IN DYNAMIC NETWORKS USING K W – STRUCTURAL DIV...
IDENTITY DISCLOSURE PROTECTION IN DYNAMIC NETWORKS USING K W – STRUCTURAL DIV...IJITE
 
Avoiding Anonymous Users in Multiple Social Media Networks (SMN)
Avoiding Anonymous Users in Multiple Social Media Networks (SMN)Avoiding Anonymous Users in Multiple Social Media Networks (SMN)
Avoiding Anonymous Users in Multiple Social Media Networks (SMN)paperpublications3
 
A MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYING
A MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYINGA MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYING
A MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYINGijaia
 
A Machine Learning Ensemble Model for the Detection of Cyberbullying
A Machine Learning Ensemble Model for the Detection of CyberbullyingA Machine Learning Ensemble Model for the Detection of Cyberbullying
A Machine Learning Ensemble Model for the Detection of Cyberbullyinggerogepatton
 
IRJET - Fake News Detection: A Survey
IRJET -  	  Fake News Detection: A SurveyIRJET -  	  Fake News Detection: A Survey
IRJET - Fake News Detection: A SurveyIRJET Journal
 
IRJET - Unauthorized Terror Attack Tracking System using Web Usage Mining
IRJET - Unauthorized Terror Attack Tracking System using Web Usage MiningIRJET - Unauthorized Terror Attack Tracking System using Web Usage Mining
IRJET - Unauthorized Terror Attack Tracking System using Web Usage MiningIRJET Journal
 
IRJET- Monitoring Suspicious Discussions on Online Forums using Data Mining
IRJET- Monitoring Suspicious Discussions on Online Forums using Data MiningIRJET- Monitoring Suspicious Discussions on Online Forums using Data Mining
IRJET- Monitoring Suspicious Discussions on Online Forums using Data MiningIRJET Journal
 
A study of cyberbullying detection using Deep Learning and Machine Learning T...
A study of cyberbullying detection using Deep Learning and Machine Learning T...A study of cyberbullying detection using Deep Learning and Machine Learning T...
A study of cyberbullying detection using Deep Learning and Machine Learning T...IRJET Journal
 
A study of cyberbullying detection using Deep Learning and Machine Learning T...
A study of cyberbullying detection using Deep Learning and Machine Learning T...A study of cyberbullying detection using Deep Learning and Machine Learning T...
A study of cyberbullying detection using Deep Learning and Machine Learning T...IRJET Journal
 
Development of a Web Application for Fake News Classification using Machine l...
Development of a Web Application for Fake News Classification using Machine l...Development of a Web Application for Fake News Classification using Machine l...
Development of a Web Application for Fake News Classification using Machine l...IRJET Journal
 
IRJET - An Automated System for Detection of Social Engineering Phishing Atta...
IRJET - An Automated System for Detection of Social Engineering Phishing Atta...IRJET - An Automated System for Detection of Social Engineering Phishing Atta...
IRJET - An Automated System for Detection of Social Engineering Phishing Atta...IRJET Journal
 
IRJET- Authentic News Summarization
IRJET-  	  Authentic News SummarizationIRJET-  	  Authentic News Summarization
IRJET- Authentic News SummarizationIRJET Journal
 
A Paper on Web Data Segmentation for Terrorism Detection using Named Entity R...
A Paper on Web Data Segmentation for Terrorism Detection using Named Entity R...A Paper on Web Data Segmentation for Terrorism Detection using Named Entity R...
A Paper on Web Data Segmentation for Terrorism Detection using Named Entity R...IRJET Journal
 
Detection of Fake News Using Machine Learning
Detection of Fake News Using Machine LearningDetection of Fake News Using Machine Learning
Detection of Fake News Using Machine LearningIRJET Journal
 
Phishing Websites Detection Using Back Propagation Algorithm: A Review
Phishing Websites Detection Using Back Propagation Algorithm: A ReviewPhishing Websites Detection Using Back Propagation Algorithm: A Review
Phishing Websites Detection Using Back Propagation Algorithm: A Reviewtheijes
 
A Model for Encryption of a Text Phrase using Genetic Algorithm
A Model for Encryption of a Text Phrase using Genetic AlgorithmA Model for Encryption of a Text Phrase using Genetic Algorithm
A Model for Encryption of a Text Phrase using Genetic Algorithmijtsrd
 

Similaire à Terrorism Analysis through Social Media using Data Mining (20)

A SYSTEMATIC REVIEW ON MACHINE LEARNING INSIDER THREAT DETECTION MODELS, DATA...
A SYSTEMATIC REVIEW ON MACHINE LEARNING INSIDER THREAT DETECTION MODELS, DATA...A SYSTEMATIC REVIEW ON MACHINE LEARNING INSIDER THREAT DETECTION MODELS, DATA...
A SYSTEMATIC REVIEW ON MACHINE LEARNING INSIDER THREAT DETECTION MODELS, DATA...
 
Fake News Detection Using Machine Learning
Fake News Detection Using Machine LearningFake News Detection Using Machine Learning
Fake News Detection Using Machine Learning
 
BINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNING
BINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNINGBINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNING
BINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNING
 
A REVIEW ON MACHINE LEARNING TECHNIQUES ON SOCIAL MEDIA DATA FOR POLICY MAKING
A REVIEW ON MACHINE LEARNING TECHNIQUES ON SOCIAL MEDIA DATA FOR POLICY MAKINGA REVIEW ON MACHINE LEARNING TECHNIQUES ON SOCIAL MEDIA DATA FOR POLICY MAKING
A REVIEW ON MACHINE LEARNING TECHNIQUES ON SOCIAL MEDIA DATA FOR POLICY MAKING
 
IDENTITY DISCLOSURE PROTECTION IN DYNAMIC NETWORKS USING K W – STRUCTURAL DIV...
IDENTITY DISCLOSURE PROTECTION IN DYNAMIC NETWORKS USING K W – STRUCTURAL DIV...IDENTITY DISCLOSURE PROTECTION IN DYNAMIC NETWORKS USING K W – STRUCTURAL DIV...
IDENTITY DISCLOSURE PROTECTION IN DYNAMIC NETWORKS USING K W – STRUCTURAL DIV...
 
Avoiding Anonymous Users in Multiple Social Media Networks (SMN)
Avoiding Anonymous Users in Multiple Social Media Networks (SMN)Avoiding Anonymous Users in Multiple Social Media Networks (SMN)
Avoiding Anonymous Users in Multiple Social Media Networks (SMN)
 
A MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYING
A MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYINGA MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYING
A MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYING
 
A Machine Learning Ensemble Model for the Detection of Cyberbullying
A Machine Learning Ensemble Model for the Detection of CyberbullyingA Machine Learning Ensemble Model for the Detection of Cyberbullying
A Machine Learning Ensemble Model for the Detection of Cyberbullying
 
IRJET - Fake News Detection: A Survey
IRJET -  	  Fake News Detection: A SurveyIRJET -  	  Fake News Detection: A Survey
IRJET - Fake News Detection: A Survey
 
IRJET - Unauthorized Terror Attack Tracking System using Web Usage Mining
IRJET - Unauthorized Terror Attack Tracking System using Web Usage MiningIRJET - Unauthorized Terror Attack Tracking System using Web Usage Mining
IRJET - Unauthorized Terror Attack Tracking System using Web Usage Mining
 
IRJET- Monitoring Suspicious Discussions on Online Forums using Data Mining
IRJET- Monitoring Suspicious Discussions on Online Forums using Data MiningIRJET- Monitoring Suspicious Discussions on Online Forums using Data Mining
IRJET- Monitoring Suspicious Discussions on Online Forums using Data Mining
 
A study of cyberbullying detection using Deep Learning and Machine Learning T...
A study of cyberbullying detection using Deep Learning and Machine Learning T...A study of cyberbullying detection using Deep Learning and Machine Learning T...
A study of cyberbullying detection using Deep Learning and Machine Learning T...
 
A study of cyberbullying detection using Deep Learning and Machine Learning T...
A study of cyberbullying detection using Deep Learning and Machine Learning T...A study of cyberbullying detection using Deep Learning and Machine Learning T...
A study of cyberbullying detection using Deep Learning and Machine Learning T...
 
Development of a Web Application for Fake News Classification using Machine l...
Development of a Web Application for Fake News Classification using Machine l...Development of a Web Application for Fake News Classification using Machine l...
Development of a Web Application for Fake News Classification using Machine l...
 
IRJET - An Automated System for Detection of Social Engineering Phishing Atta...
IRJET - An Automated System for Detection of Social Engineering Phishing Atta...IRJET - An Automated System for Detection of Social Engineering Phishing Atta...
IRJET - An Automated System for Detection of Social Engineering Phishing Atta...
 
IRJET- Authentic News Summarization
IRJET-  	  Authentic News SummarizationIRJET-  	  Authentic News Summarization
IRJET- Authentic News Summarization
 
A Paper on Web Data Segmentation for Terrorism Detection using Named Entity R...
A Paper on Web Data Segmentation for Terrorism Detection using Named Entity R...A Paper on Web Data Segmentation for Terrorism Detection using Named Entity R...
A Paper on Web Data Segmentation for Terrorism Detection using Named Entity R...
 
Detection of Fake News Using Machine Learning
Detection of Fake News Using Machine LearningDetection of Fake News Using Machine Learning
Detection of Fake News Using Machine Learning
 
Phishing Websites Detection Using Back Propagation Algorithm: A Review
Phishing Websites Detection Using Back Propagation Algorithm: A ReviewPhishing Websites Detection Using Back Propagation Algorithm: A Review
Phishing Websites Detection Using Back Propagation Algorithm: A Review
 
A Model for Encryption of a Text Phrase using Genetic Algorithm
A Model for Encryption of a Text Phrase using Genetic AlgorithmA Model for Encryption of a Text Phrase using Genetic Algorithm
A Model for Encryption of a Text Phrase using Genetic Algorithm
 

Plus de IRJET Journal

TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...IRJET Journal
 
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURESTUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTUREIRJET Journal
 
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...IRJET Journal
 
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsEffect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsIRJET Journal
 
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...IRJET Journal
 
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...IRJET Journal
 
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...IRJET Journal
 
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...IRJET Journal
 
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASA REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASIRJET Journal
 
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...IRJET Journal
 
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProP.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProIRJET Journal
 
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...IRJET Journal
 
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemSurvey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemIRJET Journal
 
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesReview on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesIRJET Journal
 
React based fullstack edtech web application
React based fullstack edtech web applicationReact based fullstack edtech web application
React based fullstack edtech web applicationIRJET Journal
 
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...IRJET Journal
 
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.IRJET Journal
 
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...IRJET Journal
 
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignMultistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignIRJET Journal
 
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...IRJET Journal
 

Plus de IRJET Journal (20)

TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
 
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURESTUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
 
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
 
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsEffect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil Characteristics
 
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
 
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
 
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
 
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
 
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASA REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADAS
 
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
 
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProP.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
 
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
 
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemSurvey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare System
 
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesReview on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridges
 
React based fullstack edtech web application
React based fullstack edtech web applicationReact based fullstack edtech web application
React based fullstack edtech web application
 
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
 
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
 
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
 
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignMultistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
 
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
 

Dernier

Power System electrical and electronics .pptx
Power System electrical and electronics .pptxPower System electrical and electronics .pptx
Power System electrical and electronics .pptxMUKULKUMAR210
 
SATELITE COMMUNICATION UNIT 1 CEC352 REGULATION 2021 PPT BASICS OF SATELITE ....
SATELITE COMMUNICATION UNIT 1 CEC352 REGULATION 2021 PPT BASICS OF SATELITE ....SATELITE COMMUNICATION UNIT 1 CEC352 REGULATION 2021 PPT BASICS OF SATELITE ....
SATELITE COMMUNICATION UNIT 1 CEC352 REGULATION 2021 PPT BASICS OF SATELITE ....santhyamuthu1
 
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptxVertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptxLMW Machine Tool Division
 
Gender Bias in Engineer, Honors 203 Project
Gender Bias in Engineer, Honors 203 ProjectGender Bias in Engineer, Honors 203 Project
Gender Bias in Engineer, Honors 203 Projectreemakb03
 
Transforming Process Safety Management: Challenges, Benefits, and Transition ...
Transforming Process Safety Management: Challenges, Benefits, and Transition ...Transforming Process Safety Management: Challenges, Benefits, and Transition ...
Transforming Process Safety Management: Challenges, Benefits, and Transition ...soginsider
 
Dev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & LoggingDev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & LoggingMarian Marinov
 
Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Bahzad5
 
Guardians and Glitches: Navigating the Duality of Gen AI in AppSec
Guardians and Glitches: Navigating the Duality of Gen AI in AppSecGuardians and Glitches: Navigating the Duality of Gen AI in AppSec
Guardians and Glitches: Navigating the Duality of Gen AI in AppSecTrupti Shiralkar, CISSP
 
Mohs Scale of Hardness, Hardness Scale.pptx
Mohs Scale of Hardness, Hardness Scale.pptxMohs Scale of Hardness, Hardness Scale.pptx
Mohs Scale of Hardness, Hardness Scale.pptxKISHAN KUMAR
 
Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...sahb78428
 
Design of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptxDesign of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptxYogeshKumarKJMIT
 
Modelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovationsModelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovationsYusuf Yıldız
 
sdfsadopkjpiosufoiasdoifjasldkjfl a asldkjflaskdjflkjsdsdf
sdfsadopkjpiosufoiasdoifjasldkjfl a asldkjflaskdjflkjsdsdfsdfsadopkjpiosufoiasdoifjasldkjfl a asldkjflaskdjflkjsdsdf
sdfsadopkjpiosufoiasdoifjasldkjfl a asldkjflaskdjflkjsdsdfJulia Kaye
 
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...Amil baba
 
Basic Principle of Electrochemical Sensor
Basic Principle of  Electrochemical SensorBasic Principle of  Electrochemical Sensor
Basic Principle of Electrochemical SensorTanvir Moin
 
cloud computing notes for anna university syllabus
cloud computing notes for anna university syllabuscloud computing notes for anna university syllabus
cloud computing notes for anna university syllabusViolet Violet
 
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...Sean Meyn
 

Dernier (20)

Power System electrical and electronics .pptx
Power System electrical and electronics .pptxPower System electrical and electronics .pptx
Power System electrical and electronics .pptx
 
SATELITE COMMUNICATION UNIT 1 CEC352 REGULATION 2021 PPT BASICS OF SATELITE ....
SATELITE COMMUNICATION UNIT 1 CEC352 REGULATION 2021 PPT BASICS OF SATELITE ....SATELITE COMMUNICATION UNIT 1 CEC352 REGULATION 2021 PPT BASICS OF SATELITE ....
SATELITE COMMUNICATION UNIT 1 CEC352 REGULATION 2021 PPT BASICS OF SATELITE ....
 
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptxVertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
Vertical- Machining - Center - VMC -LMW-Machine-Tool-Division.pptx
 
計劃趕得上變化
計劃趕得上變化計劃趕得上變化
計劃趕得上變化
 
Gender Bias in Engineer, Honors 203 Project
Gender Bias in Engineer, Honors 203 ProjectGender Bias in Engineer, Honors 203 Project
Gender Bias in Engineer, Honors 203 Project
 
Transforming Process Safety Management: Challenges, Benefits, and Transition ...
Transforming Process Safety Management: Challenges, Benefits, and Transition ...Transforming Process Safety Management: Challenges, Benefits, and Transition ...
Transforming Process Safety Management: Challenges, Benefits, and Transition ...
 
Dev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & LoggingDev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & Logging
 
Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)
 
Guardians and Glitches: Navigating the Duality of Gen AI in AppSec
Guardians and Glitches: Navigating the Duality of Gen AI in AppSecGuardians and Glitches: Navigating the Duality of Gen AI in AppSec
Guardians and Glitches: Navigating the Duality of Gen AI in AppSec
 
Mohs Scale of Hardness, Hardness Scale.pptx
Mohs Scale of Hardness, Hardness Scale.pptxMohs Scale of Hardness, Hardness Scale.pptx
Mohs Scale of Hardness, Hardness Scale.pptx
 
Présentation IIRB 2024 Marine Cordonnier.pdf
Présentation IIRB 2024 Marine Cordonnier.pdfPrésentation IIRB 2024 Marine Cordonnier.pdf
Présentation IIRB 2024 Marine Cordonnier.pdf
 
Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...
 
Design of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptxDesign of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptx
 
Modelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovationsModelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovations
 
sdfsadopkjpiosufoiasdoifjasldkjfl a asldkjflaskdjflkjsdsdf
sdfsadopkjpiosufoiasdoifjasldkjfl a asldkjflaskdjflkjsdsdfsdfsadopkjpiosufoiasdoifjasldkjfl a asldkjflaskdjflkjsdsdf
sdfsadopkjpiosufoiasdoifjasldkjfl a asldkjflaskdjflkjsdsdf
 
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
Best-NO1 Best Rohani Amil In Lahore Kala Ilam In Lahore Kala Jadu Amil In Lah...
 
Litature Review: Research Paper work for Engineering
Litature Review: Research Paper work for EngineeringLitature Review: Research Paper work for Engineering
Litature Review: Research Paper work for Engineering
 
Basic Principle of Electrochemical Sensor
Basic Principle of  Electrochemical SensorBasic Principle of  Electrochemical Sensor
Basic Principle of Electrochemical Sensor
 
cloud computing notes for anna university syllabus
cloud computing notes for anna university syllabuscloud computing notes for anna university syllabus
cloud computing notes for anna university syllabus
 
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
 

Terrorism Analysis through Social Media using Data Mining

  • 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3569 Terrorism Analysis through Social Media using Data Mining Shamika Karnik1, Sonal Singh2, Sahithi Shetty3, Sujata Kullur4 1,2,3 Student, Dept. of Information Technology, Usha Mittal Institute of Technology, Maharashtra, India 4 Professor, Dept. of Information Technology, Usha Mittal Institute of Technology, Maharashtra, India ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - There has been a tremendous increase in internet usage in the following decade which leads to many great ideas and technologies emerging. But as they say “with good comes bad”. So, a lot of malicious activity is also noticed which has been done by unknown groups. Groups can be labelled as fraudster group, terror groups and many other unethical groups. Groups use this social media platform for extracting information, and this piece of information is used by them to expand terrorist activities. This has resulted as a growing activity over the past decades. The basic idea behind this is to put an end to such kind of activities or curb this activity through technology. This paper introduces various deep learning approaches applied to the task of classifying terrorism through toxicity in online comments. Out of which the impact of Deep Neural Network(DNN), Convolutional Neural Networks (CNN), together with word and character-level embeddings, on identifying toxicity in text is implemented. The aim is to provide both the models DNN and CNN because of their capability to provide appropriate results with the help of technical analysis of the data set. The objective is to compare both the models and use the best one suited when it comes to a particular company data set. The results obtained show that the individual models work well when the data provided suits the model and appropriate parameter values are set. The accuracy of the models for each attribute is over 90%. Both the models can prove to be an asset to social media users. Thus, the paper presented provides models which can predict the percentage of a particular tweet and classify it into 6 labels: toxicity, severe toxicity, obscenity, threat, insult or identity hate. Key Words: Social media, Terrorist activities, Deep Neural Network, Convolutional Neural Network, Deep Learning, GUI. 1. INTRODUCTION Terror teams use social media as a medium to extract data and recruit’s violence within the society. Social media operate through world platforms with open access that leave digital signatures for enforcement agencies to track them down. Successful operations to curb malicious activities and track those accountable are performed with the assistance of open- source data. By acting smoothly on this obtainable data, it conjointly becomes attainable to prevent incidents before they occur. Terrorist organisations operate in such a way that the social networks ought to be able to give the primary pur- pose of contact with potential candidates for accomplishment. Once initial contact is established additional communication is shifted to associate encrypted channels wherever tracking becomes nearly impossible, which is further complicated by privacy and protection laws prevalent in various countries around the world. Conversational toxicity is a difficulty that may lead people both to prevent genuinely expressing them- selves and to prevent seeking others’ opinions out of fear of abuse/harassment. The goal of this project is to use deep learning to spot terrorism through toxicity in text, which can be accustomed to help deter users from posting potentially hurtful messages, craft more civil arguments when engaging in discourse with others, and to determine the toxicity of other users’ comments. This project aims to implement various deep learning mod- els - specifically multilayer perceptron (MLP),Deep Neural Networks(DNN) and Convolutional Neural Networks (CNN) - to tackle the above task, assessing these models’ performances on both binary and multi-label classification tasks. Our project also studies the applications of those models at both word-level and character-level granularities. 2. REVIEW OF LITERATURE The basis of study idea: The fastest growing area within the research is web data processing. It consists of web data processing, web structure mining, and website mining. Web data mining is that the process of discovering the users accessing pattern from the online data logs. the net structure mining is helpful in discovering the knowledge from the structure of the hyperlinks. The Paper presented by George Kalpakis, Theodora Tsikrika, Stefanos Vrochidis and Ioannis Kompat- siaris their have examine a social media network consisting of terrorism related Twitter accounts. Our data were collected through asocial media discovery tool executing queries on the Twitter API (https://dev.twitter.com/) employing a set of
  • 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3570 Arabic keywords associated with terrorists’ propaganda. and next their examine which centrality measure is in a position to detect the foremost influential Twitter user(s) and limit the communication effectively within the terrorist network.(1) The paper presented by Taiwo Kolajo, Olawande Daramola is to present how big data will be accustomed prevent and combat terrorism in developing countries. First, we present a bird-eye view of the analytical procedure for handling Big Data for terrorism detection, second, the architectural framework, thereafter, an outline of key components of the architecture and lastly, a use case scenario. during this paper, a use case of Social Media Analysis for Combating Terrorism (SMACT) Model was also presented so as to demonstrate the plausibility of its implemen- tation to resolve real security problems that relates to terrorism.(2) The paper presented by Ali Alzahrani, Khalid Bashir Bajwa, Turki Alghamdi and Hanaa Aldahawi their presented the methods utilized by terrorists to spread their messages using social media. it’s understood that containing terrorism- related material on social media is critical. We analysed the associated problems and proposed strategies towards an answer for containment of terrorism-related activities. The proposed strategy includes the employment of linguistic communication processing to create and expand a dataset by searching for terrorist related data on social networks, the reduction of the info using data sampling techniques, the employment of information mining methods on reduced data to spot the patterns and extract useful information and therefore the use of social network analysis to uncover the associations and relationship between individuals and terrorist groups, their structure and their modes of operations.(3) The Journal written by Aakash Negandhi, Soham Gawas, Prem Bhatt, Priya Porwal during this the system detects patterns and relevant information in texts in websites using data processing. The web site will have these characteristics: Load balancing, easy accessibility, user friendly , efficient and reliable and simple maintenance. This technique has used basic data processing moreover as a web mining concept . They used Visual Studio and Sql Server 2008 to make and record the project.(4) The article written by J. Kiruba, P. Sumitha, K. Monisha, S. Vaishnavi during this the system delivers event notification which is employed to watch the activities and delivers notification consistent with the investigation knowledge. The monitored population is unbalanced so the entire population of internet users is really near low, that’s zero. it’s not expected that the terrorists activities on the net to be a stable either-in. This study demonstrates how to use search engines to categorise websites into the categories of terrorism and anti-terrorism.This study results the concepts and methods to detect terrorists and their behaviour and their supporters who supports for terror related activities in society using an online access.(5) The journal written by Mrs. T. Suvarna Kumari, Mr. Narsaiah Putta during this framework will check website pages whether a page is advancing fear based oppression. This framework will characterize the web site pages into different classes and kind them fittingly. There are two highlights utilized during this framework that’s information mining and web mining. During this paper, the info pre-handling could be a significant undertaking of TTUM application. Accordingly web mining procedure will be utilized for distinguishing and maintaining a strategic distance from fear dangers led to by psychological oppressors everywhere throughout the planet.(6) 3. METHODOLOGY This paper aims to make the simplest model to predict and analyze the epochs values for the Terrorism Analysis. The paper presents two models CNN and DNN for the analysis which can help the concerned officials to create a more informed decision. The structure of the model presented is as shown in figure below. The software framework is made using python for the 2 algorithms of CNN and DNN. 3.1 Dataset Cleaning and filtering of the data set is done to remove duplicate records, normalize the values, accounting for missing data and removing irrelevant data items. The training data set is provided to the classifier as input. This classified data is als used for the purpose of testing. The system will operate mainly in two stages: ● Training phase ● Testing phase
  • 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3571 Fig -1: Model Architecture 3.2 Training Phase Training a model simply means learning (determining) good values for all the weights and the bias from labeled examples. The goal of training a model is to find a set of weights and biases that have low loss, on average, across all examples. Classification assumes labeled data: we know how many classes there are, and for each class we have examples (labeled data). 3.3 Convolutional Neural Network Convolutional Neural Network is a class of deep neural networks which is used in Computer Vision. A CNN generally comprises three layers: a convolutional layer, a pooling layer, and a totally connected layer. 3.3.1) Convolution Layer: The convolution layer is the core building block of the CNN.It carries the most portion of the network’s computational load. This layer conducts a real between two matrices, one of which is a set of learnable parameters referred to as a kernel, and the other is the restricted region of the receptive field. The kernel is smaller in size than a picture, but it has more depth. A stride is the size of the kernel when it slides. If we consider an input of size W x W x D and Dout number of kernels with a spatial size of F with stride S and amount of padding P, then the scale of output volume will be calculated by the formula:Formula for Convolution Layer: Wout = ((W − F + 2P )/S) + 1 (1) It will give an output volume of size Wout x Wout x Dout. 3.3.2) Pooling Layer: The pooling layer is responsible for replacing the network’s output at specific points by calculating a summary statistic of neighboring outputs. This minimizes the representation’s spatial size, which reduces the amount of computation and weights required. If we have an activation map of size W x W x D, a pooling kernel of spatial size F, and stride S, then the scale of output volume will be calculated by the subsequent formula: Formula for Padding Layer: Wout = ((W − F )/S) + 1 (2) It will give an output volume of size Wout x Wout x D. 3.3.3) Fully Connected Layer: In this layer, neurons have full connectivity with all other neurons within the preceding and succeeding layer as seen in regular FCNN. A matrix operation followed by a bias effect can be used to calculate it. The FC layer aids in the mapping of representations between the input and output. Fig -2: CNN architecture for text classification,by researchgate.net 3.4 Deep Neural Network A deep neural network (DNN) is a synthetic neural network with multiple layers between the input and output layers.It is a set of neurons organized in a sequence of multiple layers. Here,the neurons receive input from the neuron activations from the previous layer, and perform
  • 4. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3572 an easy computation for example we use a weighted sum of the input followed by a nonlinear activation. The neurons of this network jointly implement a posh nonlinear mapping from the input to the output. This mapping is learned from the information by adapt- ing the weights of every neuron with the assistance of a way called error backpropagation. A deep neural network (DNN) will be considered as stacked neural networks, i.e., networks composed of several layers. FF-DNN, also called multilayer perceptrons (MLP), are because the name suggests DNNs where there’s quite one hidden layer and therefore the network moves in barely forward direction (no loopback). These neural networks are well-suited to both classification and prediction. For spoken LID, we use the classification approach. When the FF-DNN is employed as a classifier, the input and output nodes will match the input features and output classes. The most important concepts in an exceedingly FF-DNN are weights, biases, nonlinear activation and backpropagation. The input layer has four elements which are I-1, I-2, I-3, and I-4. They define an input, I = . What we want is to seek out one or more patterns from the entities of the input, so those patterns are accustomed to classify one output from the opposite. so as to try and do that, we devise a variety of hidden units with activation functions. Nonlinear activation functions like Sigmoid, tanh, ReLU are accustomed to form a pattern of active hidden units. Let’s assume H-13, H-14, H-17, H-22, H-23, H-26,H-32, H- 33, H-36, and H-37 are needed for active output O-1. To achieve this, we need to adjust the weights and biases in such a way that these hidden nodes are activated by the activation function. Firstly, the weights and biases are randomly initialized. Later, we train this network with tens of thousands of inputs. We make use of backpropagation of error to adjust weights and biases, so that the suitable values among them will activate the hidden neurons. The set of weights and biases are called feature sets or kernels., which will be used to uniquely identify a particular output.(8) Fig -3: Text classification using a multilayer deep neural network architecture, via researchgate.net 3.5 Comparison between the two models The two models were compared and supported the methods employed for pre-processing, and processing the info for predictions, the following table shows the comparison between them. Comparison Between CNN and DNN Sr No. CNN DNN 1. Convolutional neural networks (CNN) uses a vari- ation of multilayer percep- trons and contains one or more convolutional layers that may be either entirely connected or pooled. Deep Neural Network (DNN) is comparable to artificial neural networks and aims to mimic the data processing of the brain. 2. In CNN rather than weights we use kernels that result in weight sharing. In DNN there’s no Weight sharing. 3. CNN uses a convolution operation which represents a selected filter. DNN focuses more on data from input represented by a bunch of non- linear functions. 4. Consists of multiple layers which are convolutional layer, pooling layer, fully connected layer, and nor- malising layer. Consists of more than 1 hidden layer. 5. When data flows from input layer to output layer, CNN remembers the input topology. When data flows from input layer to output layer,DNN forgets the input topology. 6. Automatically detects the important features with no human supervision. Operating of neural networks should be trained under human supervision. Table -1: Comparison between the models
  • 5. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3573 3.6 Testing Phase Testing phase involves the prediction of unknown data sample. The test set is a set of observations used to evaluate the performance of the model using some performance metric. It is important that no observations from the training set are included in the test set. 4. RESULTS Testing phase involves the prediction of unknown data sample. The test set is a set of observations used to evaluate the performance of the model using some performance metric. It is important that no observations from the training set are included in the test set. 4.1 DNN Model Results It was observed that the number of epochs highly impacted the accuracy of the model. Also, the model performed well when a large dataset was included. The accuracy using the DNN model was 97.21% . Fig -4: Training and Validation accuracy by DNN model Fig -5: Training and Validation loss by DNN model 4.2 CNN Model Results The model was trained using 1D Convolutional Layer and tested. The accuracy using CNN model was 97.64% . Fig -6: Training and Validation accuracy by CNN model Fig -7: Training and Validation loss by CNN model 5. CONCLUSIONS Social media is said to be a trend nowadays which has integrated technology, social interactions, construction of words, pictures, videos and audios. It helps to induce access to friends, tweets and user credentials. The method of Extraction and Analysis is the challenging attribute in Social Media because the data is dynamic and data is unstructured in numerous sites. The project is principally for the scholars to assist them in understanding the steps of extracting content from different sites and are available up with new advancement in developing applications by using the active data. The info Mining practices and algorithms is to develop different applications and help in improving the status of the marketing field. This is often our initial study which supplies basics about a way to start
  • 6. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3574 with the applying development. Further studies are added with improved algorithms and process of application development. The proposed model is currently offline in future work; it is extended for real-time Twitter data streaming to predict further crimes. More crime classes will be added to make the system efficient and robust. ACKNOWLEDGEMENT We have a great pleasure to express our gratitude to all those who have contributed and motivated us during our project work. We would like to express my special thanks to our guide Prof. Sujata Kullur as well as our principal Dr. Shikha Nema who gave gave us the golden opportunity to do this wonderful project on the topic: Terrorism analysis through social media using data mining, which also helped us in doing a lot of Research and we came to know about so many new things. We would also like to thank Dr. Sanjay Shitole and Prof. Mohan Bonde for their valuable inputs in completion of our project. We are really thankful to them. Secondly we would also like to thank our parents and friends who helped us a lot in finalizing this project within the limited time frame. REFERENCES [1] Ilias Gialampoukidis, I., Kalpakis, G., Tsikrika, T., Vrochidis, S. & Kompatsiaris, I. (2016, August). Key player identification in terrorism-related social media networks using centrality measures. In 2016 European Intelligence and Security Informatics Conference (EISIC) (pp. 112- 115). [2] Taiwo Kolajo and Olawande Daramola. "Leveraging big data to combat terrorism in developing countries." In 2017 Conference on Information Communication Technology and Society (ICTAS), pp. 1-6. IEEE, 2017. [3] Alzahrani, Ali, Khalid Bashir Bajwa, Turki Alghamdi, and Hanaa Aldahawi. "Countering Terrorism on Social Media Using Big Data." (2018): 35-42. [4] Negandhi, Aakash, Soham Gawas, Prem Bhatt, and Priya Porwal. "Detect Online Spread of Terrorism Using Data Mining." IOSR Journal of Engineering (IOSRJEN) 17 (2016): 19. [5] J. Kiruba, P. Sumitha, K. Monisha, S. Vaishnavi(2019), “Enhanced Content Detection Method to Detect Online Spread of Terrorism”. [6] Mrs. T. Suvarna Kumari, Mr. Narsaiah Putta (2019),” Web Data Mining to Detect Online Spread of Terrorism”. [7] Sanskar Soni, Satyendra Singh Chouhan and Santosh Singh Rathore (March 2022),”TextConvoNet:A Convolutional Neural Network based Architecture for Text Classification”. [8] Shikha Jain, Ajit Kumar Jain and Shashi Pal Singh (Jan 2021),”A Multilayer Deep Learning Framework for Auto- content Tagging”.