Exomoons & Exorings with the Habitable Worlds Observatory I: On the Detection...
Emotion Detection in text
1. By
Kashif Kashif
University of Bradford UK
Kashif.namal@gmail.com
Muhammad Yasir
Muhammad ejaz khan
University of Camerino Italy
2. a strong feeling deriving from one's
circumstances, mood, or relationships with
others.
Emotions are complex. According to some
theories, they are a state of feeling that
results in physical and psychological changes
that influence our behavior.
3. Anticipatory emotion: Desire and Fear
Outcome Emotion: Happiness, sadness,
regret, relief
Basic Emotion
4. Emotions may be expressed by a person's
speech, facial and text based emotion
People use text messages for communication
Human recognize emotion easily but the
problem is for machine.
Machine need accurate algorithm to
recognize emotion from text
Text based recognitions also useful for
psychologist
5. Hard Sensing: sensors provide the data
sources that may be relevant to emotion
recognition such as audio, gestures, eye
gazes and brain signals
Soft Sensing: extract information from
software that already exists with the user and
analyzes it for the purpose of recognizing the
user’s emotions.
6. Sentiment Analysis also called opinion mining
Basic components of an opinion
◦ Opinion holder: A person or an organization that holds
an specific opinion on a particular object.
◦ Object: on which an opinion is expressed
◦ Opinion: a view, attitude, or appraisal on an object from
an opinion holder.
Objectives of opinion mining: many ...
We use consumer reviews of products to develop
the ideas. Need Advancement of system
Sentence Level
Document level
7. Human Computer Interaction
Robot:
Read code and exactly act like human
Individual consumers
Want to buy some thing, Review the website
Organization and business:
Opinion mining
8. Strapparava et al. (2008) developed a system for
Semantic Analysis to identify emotions in text when no
affective words exist.
Drawback.
achieved a low accuracy because it is not context sensitive.
Hancock et al. (2007)
classify emotions as positive or negative. They found that
positive emotions are expressed in text by using more
exclamation marks and words, while negative emotions are
expressed using more affective words.
Drawback
this method is limited to positive/negative
9. Ghazi et al. (2010)
used hierarchical classification to classify the
six Ekman emotions.
used multiple levels of hierarchy while
classifying emotions by first classifying
whether a sentence holds an emotion or not,
classifying the emotion as either positive or
negative
they achieved a better accuracy (+7%)
10.
11. Simple and Easy method
Find Specific word in the
sentence
Work on Three dimension
Evaluation: this show how
much a word is closed to
happy or sad
Potency: show strong and weak intensity of word
Activity: show passive or active activity of the
sentence
12. Ambiguity in keyword:
Meaning of same word could be different in
different places
Sentence without keyword:
sentence which have no keyword, then how
you find the emotion
Negation Handling:
I like this dress ,
I don’t like this dress
Multiple opinion in one sentence
13. Easy to use and straightforward method.
An extension of keyword spotting technique;
Assigns a probabilistic “affinity” for a
particular emotion to arbitrary words apart
from picking up emotional keywords.
“I avoided an accident” or “I met my friend by
accident”.
The word “accident” having been assigned a
high probability of indicating a negative
emotion.
14. When system receives the input and check the
text weather it has keyword emotion or not.
If the text is available in the text apply KBM
If not available check in the dictionary.
15. Formulate the problem differently.
The problem was to determine emotions from
input texts but now the problem is to classify
the input texts into different emotions.
Try to detect emotions based on a previously
trained classifier.
Support Vector Machine, Hidden Morkov
Model, KNN Algorithm etc
16. K nearest neighbor
Pick nearest on basis
of Distance
Find when K=5
How can I determine the value of k, the number of neighbors?
◦ In general, the larger the number of training tuples is, the larger the
value of k is
◦ To find the distance between two points use Euclidian
distance.
Nearest-neighbor classifiers can be extremely slow when
classifying test tuples O(n)
By simple presorting and arranging the stored tuples into
search tree, the number of comparisons can be reduced to
O(logN)
17. • Set of states: {s1, s2, s3…. sn}
• Process moves from one state to another
generating a
• sequence of states : s1, s2….
• Markov chain property: probability of each
subsequent state depends only on what was
the previous state:
18. You are going to find robot mood that either
rebot is happy or sad by watching movie(W),
sleeping S, Crying C, Facebook F.
X=h if you happy X=s if unknown
Y observation . w, s, c or f .
We want to answer queries, such as:
P(X=h|Y=f) ?
P(X=s|Y=c) ?
19.
20. Conditional probability
“Chance” of an event given that something
is true
Notation:
◦ P(a/b)
◦ Probability of event a, given b is true
21. U stock
D stock down
P(G) Probability of
Economic grown 70%
P(U|G) Probability of
Stock improve up
What is the probability that economy grows
and stock went up P(G|U)
22. P(UG)=P(U|G)P(G)
Called joint probability.
(70%)(80%)=56%
What is the probabilty
That economy will grow
P(G)=70%:Unconditional
P(G|U)=(P(U|G)P(G))/( P(U|G) + P(U|G’))
P(G|U)=(80%)(70%)/(80%)(70%)+(30%)(30%)
P(G|U)=56%/56%+9%=86%
23. Decision tree is a binary tree which is
represented by nodes, tree work in recursive
algorithm.
24. Rule 1:
ignore the complete sentence before word “BUT”
“We try to do our best to complete our work but it was difficult”.
remove the sentence “we try our best to complete our work”
Rule 2:
Ignore sentence or phrase after the word “as”.
“He is good as his father”. remove “his father”. remaining is
“He is good”
Rule 3:
remove the Verb to emotional word. Like “we had fun” , remove
“Had” relationship in between the word we and fun.
Rule 4:
Remove WP pronoun “What are you doing here it is not a good
place”. remaining part is “it is not a good place’ the last
sentence shows some emotions here.
25. Data take the sentence
Start with root node
For every sentence do
Extract into NP and VP
For NP do
Extract into POS
Find noun
END
For VP do
Extract into POS
Find events
Find verb
END
Repeat until all the phrases split
END
26.
27. the ability to search based on emotions
the ability to study how emotional
expression changes over time
Different algorithm used to find the solution
for detection
In Future, This system should also detect not
only the existence of keywords, but also their
linguistic information to detect emotions
more accurately
28. Kashif khan
Beng Software Engineering. University of
Bradford UK
Master Computer Science. University of
Camerino Italy
Kashif.namal@gmail.com