sentiment analysis

12
Sentiment Analysis for Twitter Priyanka Bajaj [email protected] Kamal Gurala [email protected] Faraz Alam [email protected] Ritesh Kumar Gupta [email protected] Guided By : Satarupa Guha [email protected]

Upload: prnk08

Post on 16-Jul-2015

41 views

Category:

Education


3 download

TRANSCRIPT

Sentiment Analysis for Twitter

Priyanka Bajaj [email protected] Gurala [email protected] Alam [email protected] Kumar Gupta [email protected]

Guided By : Satarupa Guha [email protected]

AGENDA

1.Introduction – Sentiment Analysis

2.About Twitter and Our Goal

3.Glossary

4.Challenges

5.Approach

6.Results and Conclusion

7.Tools and Technologies

What is Sentiment Analysis?Mechanism to extract opinions, emotions and sentiments in text

Enable us to track attitudes and feelings on the web based on blog posts, comments, reviews and tweets on different topics

Enable to track products, brands and people and determine whether they are viewed positively or negatively on the web.

acts: "The painting was more expensive than a Monet"

pinions: "I honestly don't like Monet, Pollock is the better” artist"

• An online social networking and micro blogging service

• Enables users to send and read "tweets", which are text messages limited to 140 characters, hence unambiguous

• 500 million tweets daily by 240+ million active users

• Audience varies from common man to celebrities

• Users discuss current affairs and share personal views

Our goal:Determine whether the expressed opinion in the tweets is

positive, negative or neutral. For tweets conveying both a positive and negative sentiment, choose the stronger sentiment

About

Natural Language Processing: The attempt to use programming to read and understand the meaning of text.

Semantic Analysis:

Use of Natural Language processing (NLP) to derive "sentiment," or subjective information from text.

Artificial intelligence:Using information provided by NLP and mathematics to determine whether something is negative or positive

Glossary

Challenges

• Tweets are highly unstructured and also non-grammatical

• Out of Vocabulary Words

• Lexical Variation

• Extensive usage of acronyms like asap, lol, afaik

Our System

• Tweet Downloader – Download the tweets using Twitter API

• Tokenisation – Twitter specific POS Tagger developed by ARK Social

Media Search• Preprocessing

– Replacing Emoticons by their polarity, assign scores– Remove URL, Target Mentions– Replace #text -> text, since hashtags may contribute to the

sentiment– Replace Sequence of Repeated Characters eg. ‘cooooool’

by ‘cool’ and assign higher score– Twitter specific stop word removal– Acronym expansion

System Details

• Feature Extractor

– Unigrams and Bigrams

– Polarity Score of the Tweet (f1)– Count of Positive/Negative Words (f2,f3)

– Maximum Positive/Negative Score for Words (f4,f5)

– Count of Positive/Negative Emoticons and assign scores(contibutes to all f1,f2,f3,f4,f5)

– Positive/Negative special POS Tags Polarity Score

• Classifier and Prediction

– Features extracted are fed into to SVM classifier

– Model built used to predict sentiment of new tweets

System Details Contd.

Results and ConclusionA baseline model by taking the unigrams, and compare it with the bigrams and lexicon features model

Sub-Task Baseline Model Feature Based Model

Sentence Based 49.81% 57.85%

Accuracy F1 Score (f-Measure)

Sub-Task Baseline Model Feature Based Model

Sentence Based 55.56 61.17

• We investigated two kinds of models: Baseline and Feature Based Models

• For our feature-based approach, feature analysis reveals that the most important features are bigrams and those that combine the prior polarity of words and their parts-of-speech tags

1. Concepts of Data Mining and Information Retrieval

2. Python Language

3. Java, Eclipse

4. Support Vector Machine(SVM) Theory

5. LIBSVM package for accuracy and f-Measure

6. Twitter.inc API for training set

7. NLTK

8. Shell Script for integration

Tools and Technology Used

Thank You