SlideShare une entreprise Scribd logo
1  sur  12
A Sentiment-Based Approach to Twitter User
Recommendation
Davide Feltoni Gurini, Fabio Gasparetti, Alessandro Micarelli, and Giuseppe Sansonetti
Department of Computer Science and Automation
Artificial Intelligence Laboratory,
Roma Tre University
Via della Vasca Navale, 79, 00146 Rome, Italy

Twitter - @davide_feltoni
RSWEB 2013 – Hong Kong, 13 Oct 2013
A Sentiment-Based Approach to Twitter User
Recommendation

Outline
•
•
•
•

Introduction and Motivations
SVO Weighting Schema
Dataset and Evaluation Results
Conclusions and Future Works

5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

2
A Sentiment-Based Approach to Twitter User
Recommendation

Social Network: Twitter

• Free data rich of text, multimedia
contents and social relationships
• " Followers and " and "followees"
• Relationships are mainly formed
by users that share similar interests

5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

3
A Sentiment-Based Approach to Twitter User
Recommendation

User Profiling
Bag of Words -> Keywords
Bag of Concepts -> Concepts

Concepts
Hashtag #
Named-entities
Events

Metadata used to categorize topic of the tweet by keyword

Persons, locations, companies, products, ..
Tv-shows, events with a great deal of media attention

5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

4
A Sentiment-Based Approach to Twitter User
Recommendation

Motivations
User 1

N°tweets = 93

#Politics, #Syria, ..

Democratic?

User 2

N°tweets = 84

#Politics, #Syria, ..

CNN, BBC, ..

User 3

N°tweets = 89

#Politics, #Syria, ..

Republican?

Syria Sentiment Analysis

User 1

User 2

User 3

Pos

Pos

Pos

Neg

Neg

Neg

Neu

Neu

Neu

5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

5
A Sentiment-Based Approach to Twitter User
Recommendation

Sentiment Analysis
Research Question
Can implicit sentiment analysis improve user recommendation?

5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

6
A Sentiment-Based Approach to Twitter User
Recommendation

SVO weighting schema

Similarity Function

5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

7
A Sentiment-Based Approach to Twitter User
Recommendation

Dataset
1080500 tweets
25715 users
> 30000 tweets per day

31st Jan 2013
5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

1st Mar 2013
8
A Sentiment-Based Approach to Twitter User
Recommendation

Evaluation
follow(B,A)
A

follow(A,B)

Evaluation Dataset
B

•1000 user that wrote > 50 tweet
• 805.956 tweets

Mini-batch gradient descent for parameters
α β and γ that maximize the performance

S@10: mean probability that a relevant user is in top-k position
MAP@10: average of precision value for each of the top-k recommended users
MRR: average position of a relevant user in the recommended list
5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

9
A Sentiment-Based Approach to Twitter User
Recommendation

Experimental Results
Best Parameters Achieved

J. Hannon, K. McCarthy, and B. Smyth.
Finding useful users on twitter:
twittomender the followee recommender.

5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

10
A Sentiment-Based Approach to Twitter User
Recommendation

Conclusions and Future Works
• Richer weighting schema compared with " state-of-the-art "
• Implicit sentiment analysis to improve recommendation
• Preliminary evaluation shows the benefits of the proposed
approach

•
•
•
•

Use a general dataset (Hannon et al.)
Expand concepts to Named Entities, Products, Events, …
Improve recommendation leveraging Collaborative Filtering
Sensitivity Analysis for parameters

5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong

11
THANK YOU FOR YOUR
ATTENTION

RSWEB 2013 – Hong Kong, 13 Oct 2013

Contenu connexe

Tendances

Personalizing Forum Search using Multidimensional Random Walks
Personalizing Forum Search using Multidimensional Random WalksPersonalizing Forum Search using Multidimensional Random Walks
Personalizing Forum Search using Multidimensional Random Walks
Amélie Marian
 
Final Poster for Engineering Showcase
Final Poster for Engineering ShowcaseFinal Poster for Engineering Showcase
Final Poster for Engineering Showcase
Tucker Truesdale
 

Tendances (9)

presentation29
presentation29presentation29
presentation29
 
Measuring Opinion Credibility in Twiiter
Measuring Opinion Credibility in TwiiterMeasuring Opinion Credibility in Twiiter
Measuring Opinion Credibility in Twiiter
 
Personalizing Forum Search using Multidimensional Random Walks
Personalizing Forum Search using Multidimensional Random WalksPersonalizing Forum Search using Multidimensional Random Walks
Personalizing Forum Search using Multidimensional Random Walks
 
Final Poster for Engineering Showcase
Final Poster for Engineering ShowcaseFinal Poster for Engineering Showcase
Final Poster for Engineering Showcase
 
Probabilistic Reasoner
Probabilistic ReasonerProbabilistic Reasoner
Probabilistic Reasoner
 
Analyzing User Modeling on Twitter for Personalized News Recommendations
Analyzing User Modeling on Twitter for Personalized News RecommendationsAnalyzing User Modeling on Twitter for Personalized News Recommendations
Analyzing User Modeling on Twitter for Personalized News Recommendations
 
A network based model for predicting a hashtag break out in twitter
A network based model for predicting a hashtag break out in twitter A network based model for predicting a hashtag break out in twitter
A network based model for predicting a hashtag break out in twitter
 
Cyberhate publications
Cyberhate publicationsCyberhate publications
Cyberhate publications
 
Practical Uses of Altmetrics - Hear librarians talk about how they use new me...
Practical Uses of Altmetrics - Hear librarians talk about how they use new me...Practical Uses of Altmetrics - Hear librarians talk about how they use new me...
Practical Uses of Altmetrics - Hear librarians talk about how they use new me...
 

En vedette

Twitter Data Analytics
Twitter Data AnalyticsTwitter Data Analytics
Twitter Data Analytics
rupika08
 
Twitter as a data mining source
Twitter  as  a data mining sourceTwitter  as  a data mining source
Twitter as a data mining source
Ataxo Group
 

En vedette (10)

[WWW Conference 2011]Information Credibility on Twitter
[WWW Conference 2011]Information Credibility on Twitter[WWW Conference 2011]Information Credibility on Twitter
[WWW Conference 2011]Information Credibility on Twitter
 
Mining Twitter to Understand Engineering Students' Experiences
Mining Twitter to Understand Engineering Students' ExperiencesMining Twitter to Understand Engineering Students' Experiences
Mining Twitter to Understand Engineering Students' Experiences
 
Kaplan & Haenlein - The early bird catches the news nine things you should kn...
Kaplan & Haenlein - The early bird catches the news nine things you should kn...Kaplan & Haenlein - The early bird catches the news nine things you should kn...
Kaplan & Haenlein - The early bird catches the news nine things you should kn...
 
Tutorial on Relationship Mining In Online Social Networks
Tutorial on Relationship Mining In Online Social NetworksTutorial on Relationship Mining In Online Social Networks
Tutorial on Relationship Mining In Online Social Networks
 
Identifying rumours on Twitter
Identifying rumours on TwitterIdentifying rumours on Twitter
Identifying rumours on Twitter
 
Twitter Data Analytics
Twitter Data AnalyticsTwitter Data Analytics
Twitter Data Analytics
 
Twitter as a data mining source
Twitter  as  a data mining sourceTwitter  as  a data mining source
Twitter as a data mining source
 
Slides: Epidemiological Modeling of News and Rumors on Twitter
Slides: Epidemiological Modeling of News and Rumors on TwitterSlides: Epidemiological Modeling of News and Rumors on Twitter
Slides: Epidemiological Modeling of News and Rumors on Twitter
 
Eavesdropping on the Twitter Microblogging Site
Eavesdropping on the Twitter Microblogging SiteEavesdropping on the Twitter Microblogging Site
Eavesdropping on the Twitter Microblogging Site
 
Rumor
RumorRumor
Rumor
 

Similaire à A Sentiment-Based Approach to Twitter User Recommendation

SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptxSampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
20211a05p7
 
srd117.final.512Spring2016
srd117.final.512Spring2016srd117.final.512Spring2016
srd117.final.512Spring2016
Saurabh Deochake
 

Similaire à A Sentiment-Based Approach to Twitter User Recommendation (20)

Online social network analysis with machine learning techniques
Online social network analysis with machine learning techniquesOnline social network analysis with machine learning techniques
Online social network analysis with machine learning techniques
 
Who are the top influencers and what characterizes them?
Who are the top influencers and what characterizes them?Who are the top influencers and what characterizes them?
Who are the top influencers and what characterizes them?
 
Detection and Analysis of Twitter Trending Topics via Link-Anomaly Detection
Detection and Analysis of Twitter Trending Topics via Link-Anomaly DetectionDetection and Analysis of Twitter Trending Topics via Link-Anomaly Detection
Detection and Analysis of Twitter Trending Topics via Link-Anomaly Detection
 
lms final ppt.pptx
lms final ppt.pptxlms final ppt.pptx
lms final ppt.pptx
 
Exploring Generative Models of Tripartite Graphs for Recommendation in Social...
Exploring Generative Models of Tripartite Graphs for Recommendation in Social...Exploring Generative Models of Tripartite Graphs for Recommendation in Social...
Exploring Generative Models of Tripartite Graphs for Recommendation in Social...
 
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptxSampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
 
Using Twitter as a data source: An overview of ethical challenges
Using Twitter as a data source: An overview of ethical challengesUsing Twitter as a data source: An overview of ethical challenges
Using Twitter as a data source: An overview of ethical challenges
 
Empirical Model of Supervised Learning Approach for Opinion Mining
Empirical Model of Supervised Learning Approach for Opinion MiningEmpirical Model of Supervised Learning Approach for Opinion Mining
Empirical Model of Supervised Learning Approach for Opinion Mining
 
SENTIMENT ANALYSIS OF SOCIAL MEDIA DATA USING DEEP LEARNING
SENTIMENT ANALYSIS OF SOCIAL MEDIA DATA USING DEEP LEARNINGSENTIMENT ANALYSIS OF SOCIAL MEDIA DATA USING DEEP LEARNING
SENTIMENT ANALYSIS OF SOCIAL MEDIA DATA USING DEEP LEARNING
 
Movies recommendation system in R Studio, Machine learning
Movies recommendation system in  R Studio, Machine learning Movies recommendation system in  R Studio, Machine learning
Movies recommendation system in R Studio, Machine learning
 
IRJET- Effective Countering of Communal Hatred During Disaster Events in Soci...
IRJET- Effective Countering of Communal Hatred During Disaster Events in Soci...IRJET- Effective Countering of Communal Hatred During Disaster Events in Soci...
IRJET- Effective Countering of Communal Hatred During Disaster Events in Soci...
 
Lee Sung Eob Mastersthesisproposal03
Lee Sung Eob Mastersthesisproposal03Lee Sung Eob Mastersthesisproposal03
Lee Sung Eob Mastersthesisproposal03
 
IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...
IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...
IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...
 
Twitter_Hashtag_Prediction.pptx
Twitter_Hashtag_Prediction.pptxTwitter_Hashtag_Prediction.pptx
Twitter_Hashtag_Prediction.pptx
 
Lecture 5: How to make the Social Web Personalized? (VU Amsterdam Social Web ...
Lecture 5: How to make the Social Web Personalized? (VU Amsterdam Social Web ...Lecture 5: How to make the Social Web Personalized? (VU Amsterdam Social Web ...
Lecture 5: How to make the Social Web Personalized? (VU Amsterdam Social Web ...
 
2.pdf
2.pdf2.pdf
2.pdf
 
Final Year PPT on Twitter App
Final Year PPT on Twitter AppFinal Year PPT on Twitter App
Final Year PPT on Twitter App
 
srd117.final.512Spring2016
srd117.final.512Spring2016srd117.final.512Spring2016
srd117.final.512Spring2016
 
2016 09-28 social network analysis with node-xl_emke
2016 09-28 social network analysis with node-xl_emke2016 09-28 social network analysis with node-xl_emke
2016 09-28 social network analysis with node-xl_emke
 
Open Data Infrastructures Evaluation Framework using Value Modelling
Open Data Infrastructures Evaluation Framework using Value Modelling Open Data Infrastructures Evaluation Framework using Value Modelling
Open Data Infrastructures Evaluation Framework using Value Modelling
 

Dernier

+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 

Dernier (20)

Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 

A Sentiment-Based Approach to Twitter User Recommendation

  • 1. A Sentiment-Based Approach to Twitter User Recommendation Davide Feltoni Gurini, Fabio Gasparetti, Alessandro Micarelli, and Giuseppe Sansonetti Department of Computer Science and Automation Artificial Intelligence Laboratory, Roma Tre University Via della Vasca Navale, 79, 00146 Rome, Italy Twitter - @davide_feltoni RSWEB 2013 – Hong Kong, 13 Oct 2013
  • 2. A Sentiment-Based Approach to Twitter User Recommendation Outline • • • • Introduction and Motivations SVO Weighting Schema Dataset and Evaluation Results Conclusions and Future Works 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 2
  • 3. A Sentiment-Based Approach to Twitter User Recommendation Social Network: Twitter • Free data rich of text, multimedia contents and social relationships • " Followers and " and "followees" • Relationships are mainly formed by users that share similar interests 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 3
  • 4. A Sentiment-Based Approach to Twitter User Recommendation User Profiling Bag of Words -> Keywords Bag of Concepts -> Concepts Concepts Hashtag # Named-entities Events Metadata used to categorize topic of the tweet by keyword Persons, locations, companies, products, .. Tv-shows, events with a great deal of media attention 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 4
  • 5. A Sentiment-Based Approach to Twitter User Recommendation Motivations User 1 N°tweets = 93 #Politics, #Syria, .. Democratic? User 2 N°tweets = 84 #Politics, #Syria, .. CNN, BBC, .. User 3 N°tweets = 89 #Politics, #Syria, .. Republican? Syria Sentiment Analysis User 1 User 2 User 3 Pos Pos Pos Neg Neg Neg Neu Neu Neu 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 5
  • 6. A Sentiment-Based Approach to Twitter User Recommendation Sentiment Analysis Research Question Can implicit sentiment analysis improve user recommendation? 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 6
  • 7. A Sentiment-Based Approach to Twitter User Recommendation SVO weighting schema Similarity Function 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 7
  • 8. A Sentiment-Based Approach to Twitter User Recommendation Dataset 1080500 tweets 25715 users > 30000 tweets per day 31st Jan 2013 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 1st Mar 2013 8
  • 9. A Sentiment-Based Approach to Twitter User Recommendation Evaluation follow(B,A) A follow(A,B) Evaluation Dataset B •1000 user that wrote > 50 tweet • 805.956 tweets Mini-batch gradient descent for parameters α β and γ that maximize the performance S@10: mean probability that a relevant user is in top-k position MAP@10: average of precision value for each of the top-k recommended users MRR: average position of a relevant user in the recommended list 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 9
  • 10. A Sentiment-Based Approach to Twitter User Recommendation Experimental Results Best Parameters Achieved J. Hannon, K. McCarthy, and B. Smyth. Finding useful users on twitter: twittomender the followee recommender. 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 10
  • 11. A Sentiment-Based Approach to Twitter User Recommendation Conclusions and Future Works • Richer weighting schema compared with " state-of-the-art " • Implicit sentiment analysis to improve recommendation • Preliminary evaluation shows the benefits of the proposed approach • • • • Use a general dataset (Hannon et al.) Expand concepts to Named Entities, Products, Events, … Improve recommendation leveraging Collaborative Filtering Sensitivity Analysis for parameters 5th ACM RecSys Workshop on Recommender Systems and the Social Web, 13 Oct 2013, Hong Kong 11
  • 12. THANK YOU FOR YOUR ATTENTION RSWEB 2013 – Hong Kong, 13 Oct 2013