Sentiment Analysis. (thanks to Matt Baker)

Transcription

1 Sentiment Analysis (thanks to Matt Baker)

2 Laptop Purchase will you decide?

3 Survey Says 81% internet users online product research 1+ times 20% internet users online product research daily 73-87% consumers of restaurant, hotel, service reviews reviews significantly impact purchasing decisions comscore/the Kelsey group, Online consumer-generated reviews have significant impact on offline purchase behavior, Press Release, November Quoted in Pang and Lee, 2008, Opinion Mining and Sentiment Analysis

4 Survey Says 20-99% consumers willing to pay more for 5- than 4-star-rated product 32% consumers rated online product, service, person 30% consumers posted online comment or review J. A. Horrigan, Online shopping, Pew Internet & American Life Project Report, Quoted in Pang and Lee, 2008, Opinion Mining and Sentiment Analysis

5 Definition Many scholars view sentiment analysis as the computational treatment of opinion, sentiment, and subjectivity in text * do each of these terms differ? *Pang 2008, pg. 8

6 Review of Literature Uses machine learning to assess polarity (positive, negative, neutral) in movie reviews Pang, Lee, & Vaithyanathan (2002) Evaluates sentiment based on parts of speech (adjectives and adverbs) Turney (2002)

7 Review of Literature Separates objective from subjective statements and assess polarity of opinion sentences Yu & Hatzivassiloglou (2003) Identifies valence shifters in text that can give information regarding the writer s sentiment Polanyi & Zaenen (2004)

8 Review of Literature Expands sentiment analysis to include rankings on a scale Pang & Lee (2005) Selects features from text and performs sentiment analysis on a feature level Durant & Smith (2007)

9 Twitter would you extract sentiment from Tweets?

10 Considerations Parts of speech Objective statements Subjective statements Binary classification Ranking Features Overall sentiment Domain Word position

11 Considerations Valence shifters* Words Negation Intensifiers Modal operators Irony Pronoun resolution Topic relevance Unigrams, bigrams, etc. Syntax Strength of polarity *Polanyi & Zaenen (2004)

12 Twitter Literature Sentiment word frequencies* Emoticons *** Unigrams*** Bigrams*** Parts of Speech*** *O Conner et al ***Go 2009

13 Sample reviews (negative polarity) a peculiar misfire that even tunney can't save. watching queen of the damned is like reading a research paper, with special effects tossed in. i can't remember the last time i saw worse stunt editing or cheaper action movie production values than in extreme ops. too much of nemesis has a tired, talky feel. i felt trapped and with no obvious escape for the entire 100 minutes. a baffling mixed platter of gritty realism and magic realism with a hard-to-swallow premise. an affable but undernourished romantic comedy that fails to match the freshness of the actressproducer and writer's previous collaboration, miss congeniality

14 Sample reviews (positive polarity) emerges as something rare, an issue movie that's so honest and keenly observed that it doesn't feel like one. the film provides some great insight into the neurotic mindset of all comics -- even those who have reached the absolute top of the game. offers that rare combination of entertainment and education. perhaps no picture ever made has more literally showed that the road to hell is paved with good intentions. offers a breath of the fresh air of true sophistication. a thoughtful, provocative, insistently humanizing film. not for everyone, but for those with whom it will connect, it's a nice departure from standard moviegoing fare. is it a total success? no. is it something any true film addict will want to check out? you bet. engrossing and affecting, if ultimately not quite satisfying.

15 Lexical characterizations

16 Tools: SentiWordNet

17 Tools: Opinon Lexicon

18 Online data / demos / tools Movie review data NLTK

19 Systems LingPipe: tutorial and system you can install Weka: blog and instructions R: blog and pointer to code

20 Competitions Kaggle.com

21 Methods: Linear Regression

22 Example Twitter with R* * *

23 Other applications Classifying speeches as for or against issues* Discovering the political leanings of texts** Sensing user annoyance by computers to change interaction methods*** Monitoring violent and hateful propaganda**** Tracking the world s mood***** Scanning s *Thomas, et al **Pang 2008 ***Liscombe et al ****Abassi 2007

24 References A. Abbasi, Affect intensity analysis of dark web forums, in Proceedings of Intelligence and Security Informatics (ISI), pp , Bo, Pang, and Lillian Lee. "Opinion Mining and Sentiment Analysis." Foundations & Trends in Information Retrieval 2, no. 1/2 (2008): Bo, Pang, Lillian Lee, and Shivakumar Vaithyanathan. Thumbs up? Sentiment Classification using Machine Learning Techniques. Proceedings of the Conference on Empirical Methods in Natural Language Processing. (2002). Durant, Kathleen and Michael Smith. Predicting the Political Sentiment of Web Log Posts using Supervised Machine Learning Techniques Coupled with Feature Selection Go, Alec. Twitter Sentiment Analysis J. Liscombe, G. Riccardi, and D. Hakkani-T ur, Using context to improve emotion detection in spoken dialog systems, in Interspeech, pp , M. Thomas, B. Pang, and L. Lee, Get out the vote: Determining support or opposition from congressional floor-debate transcripts, in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp , O Connor, Brandon, Ramnath Balasubramanyan, Bryan R. Routledge, and Noah A. Smith. From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series Pang, Bo and Lillian Lee. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales Polanyi, Livia and Annie Zaenen. Contextual valence shifters. Computing attitude and affect in text: Theory and applications Turney, Peter. Thumbs up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. Proceedings of the 40 th Annual Meeting of the Association for Computational Linguistics. (2002). Yu, Hong and Vasileios Hatzivassiloglou. Towards answering opinion questions: separating facts from opinions and identifying the polarity of opinion sentences. Proceedings of the 2003 conference on Empirical methods in natural language processing