1 / 228

Subjectivity and Sentiment Analysis

Subjectivity and Sentiment Analysis . Jan Wiebe Josef Ruppenhofer Swapna Somasundaran University of Pittsburgh. Want to start with acknowledgments to colleagues and students. CERATOPS Center for Extraction and Summarization of Events and Opinions in Text. Jan Wiebe, U. Pittsburgh

cornelia
Télécharger la présentation

Subjectivity and Sentiment Analysis

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Subjectivity and Sentiment Analysis Jan Wiebe Josef Ruppenhofer Swapna Somasundaran University of Pittsburgh

  2. Want to start with acknowledgments to colleagues and students ICWSM 2008

  3. CERATOPSCenter for Extraction and Summarization of Events and Opinions in Text Jan Wiebe, U. Pittsburgh Claire Cardie, Cornell U. Ellen Riloff, U. Utah

  4. Word Sense and SubjectivityLearning Multi-Lingual Subjective Language Rada Mihalcea, U. North Texas Jan Wiebe

  5. Our Student Co-Authors in Subjectivity and Sentiment Analysis • Carmen Banea North Texas • Eric Breck Cornell • Yejin Choi Cornell • Paul Hoffmann Pittsburgh • Wei-Hao Lin CMU • Sidd Patwardhan Utah • Bill Phillips Utah • Swapna Somasundaran Pittsburgh • Ves Stoyanov Cornell • Theresa Wilson Pittsburgh ICWSM 2008

  6. What is Subjectivity? • The linguisticexpression of somebody’s opinions, sentiments, emotions, evaluations, beliefs, speculations (private states) Private state: state that is not open to objective observation or verification Quirk, Greenbaum, Leech, Svartvik (1985). A Comprehensive Grammar of the English Language. ICWSM 2008

  7. Opinion Question Answering Q: What is the international reaction to the reelection of Robert Mugabe as President of Zimbabwe? ICWSM 2008

  8. Opinion Question Answering Q: What is the international reaction to the reelection of Robert Mugabe as President of Zimbabwe? A: African observers generally approved of his victory while Western Governments stronglydenounced it. Opinion QA is more complex Automatic subjectivity analysis can be helpful Stoyanov, Cardie, Wiebe EMNLP05 Somasundaran, Wilson, Wiebe, Stoyanov ICWSM07 ICWSM 2008

  9. Information Extraction “The Parliamentexplodedinto fury against the government when word leaked out…” Observation: subjectivity often causes false hits for IE Subjectivity filtering strategies to improve IERiloff, Wiebe, Phillips AAAI05 ICWSM 2008

  10. Information Extraction Recent study: several kinds of subjectivity are found in ProMed data* Goal: augment the results of IE *Program for Monitoring Emerging Diseases, a reporting system for out breaks of emerging infectious diseases and toxins maintained by the International Society for Infectious Diseases ICWSM 2008

  11. More Applications • Product review mining:What features of the ThinkPad T43 do customers like and which do they dislike? • Review classification:Is a review positive or negative toward the movie? • Tracking sentiments toward topics over time:Is anger ratcheting up or cooling down? • Prediction (election outcomes, market trends): Will Clinton or Obama win? • Etcetera! ICWSM 2008

  12. Bibliographies and Yahoo! Group • Bibliography available at www.cs.pitt.edu/~wiebe • Over 200 papers mainly from Computer Science since 2000 not complete • html • bibtex • Andrea Esuli’s bibliography http://www.ira.uka.de/bibliography/Misc/Sentiment.html • SentimentAI • http://tech.groups.yahoo.com/group/SentimentAI ICWSM 2008

  13. This Talk • Focus on • Fine-grained level rather than document level • Linguistic ambiguity: what does a system need to recognize and extract to understand subjectivity and sentiment expressed in text? • Focus more on comprehensive definitions and approaches rather than those targeting specific objects and features • Sampling of potential topics • Additional material at end of slides for reference ICWSM 2008

  14. Outline • Definitions and Annotation Schemes • Lexicon development • Contextual Polarity • Point out additional material at the end ICWSM 2008

  15. Definitions and Annotation Scheme • Manual annotation: human markup of corpora (bodies of text) • Why? • Understand the problem • Create gold standards (and training data) Wiebe, Wilson, Cardie LRE 2005 Wilson & Wiebe ACL-2005 workshop Somasundaran, Wiebe, Hoffmann, Litman ACL-2006 workshop Somasundaran, Ruppenhofer, Wiebe SIGdial 2007 Wilson 2008 PhD dissertation ICWSM 2008

  16. What is Subjectivity? • The linguisticexpression of somebody’s opinions, sentiments, emotions, evaluations, beliefs, speculations (private states) Private state: state that is not open to objective observation or verification Quirk, Greenbaum, Leech, Svartvik (1985). A Comprehensive Grammar of the English Language. ICWSM 2008

  17. Overview • Fine-grained: expression-level rather than sentence or document level • Annotate • Subjective expressions • material attributed to a source, but presented objectively ICWSM 2008

  18. Overview • Focus on three ways private states are expressed in language ICWSM 2008

  19. Direct Subjective Expressions • Direct mentions of private states The United Statesfears a spill-over from the anti-terrorist campaign. • Private states expressed in speech events “We foresaw electoral fraud but not daylight robbery,” Tsvangirai said. ICWSM 2008

  20. Expressive Subjective Elements [Banfield 1982] • “We foresaw electoral fraud but not daylight robbery,” Tsvangirai said • The part of the US human rights report about China is full of absurdities and fabrications ICWSM 2008

  21. Objective Speech Events • Material attributed to a source, but presented as objective fact The government, it added, has amended the Pakistan Citizenship Act 10 of 1951 to enable women of Pakistani descent to claim Pakistani nationality for their children born to foreign husbands. ICWSM 2008

  22. ICWSM 2008

  23. Nested Sources “The report is full of absurdities,’’ Xirao-Nima said the next day. ICWSM 2008

  24. “The report is full of absurdities,’’ Xirao-Nima said the next day. Nested Sources (Writer) ICWSM 2008

  25. “The report is full of absurdities,’’ Xirao-Nima said the next day. Nested Sources (Writer, Xirao-Nima) ICWSM 2008

  26. “The report is full of absurdities,’’ Xirao-Nima said the next day. Nested Sources (Writer Xirao-Nima) (Writer Xirao-Nima) ICWSM 2008

  27. “The report is full of absurdities,’’ Xirao-Nima said the next day. Nested Sources (Writer) (Writer Xirao-Nima) (Writer Xirao-Nima) ICWSM 2008

  28. “The report is full of absurdities,” Xirao-Nima said the next day. Objective speech event anchor:the entire sentence source: <writer> implicit: true Direct subjective anchor:said source: <writer, Xirao-Nima> intensity: high expression intensity: neutral … Expressive subjective element anchor:full of absurdities source: <writer, Xirao-Nima> intensity: high … ICWSM 2008

  29. “The US fears a spill-over’’, said Xirao-Nima, a professor of foreign affairs at the Central University for Nationalities. ICWSM 2008

  30. (Writer) “The US fears a spill-over’’, said Xirao-Nima, a professor of foreign affairs at the Central University for Nationalities. ICWSM 2008

  31. (writer, Xirao-Nima) “The US fears a spill-over’’, said Xirao-Nima, a professor of foreign affairs at the Central University for Nationalities. ICWSM 2008

  32. (writer, Xirao-Nima, US) “The US fears a spill-over’’, said Xirao-Nima, a professor of foreign affairs at the Central University for Nationalities. ICWSM 2008

  33. (Writer) (writer, Xirao-Nima, US) (writer, Xirao-Nima) “The US fears a spill-over’’, said Xirao-Nima, a professor of foreign affairs at the Central University for Nationalities. ICWSM 2008

  34. “The US fears a spill-over’’, said Xirao-Nima, a professor of foreign affairs at the Central University for Nationalities. Objective speech event anchor:the entire sentence source: <writer> implicit: true Objective speech event anchor:said source: <writer, Xirao-Nima> Direct subjective anchor:fears source: <writer, Xirao-Nima, US> intensity: medium expression intensity:medium … ICWSM 2008

  35. The report has been strongly criticized and condemned by many countries. ICWSM 2008

  36. The report has been strongly criticized and condemned by many countries. Objective speech event anchor:the entire sentence source: <writer> implicit: true Direct subjective anchor:strongly criticized and condemned source: <writer, many-countries> intensity: high expressionintensity:high … ICWSM 2008

  37. As usual, the US state Department published its annual report on human rights practices in world countries last Monday. And as usual, the portion about China contains little truth and many absurdities, exaggerations and fabrications. ICWSM 2008

  38. As usual, the US state Department published its annual report on human rights practices in world countries last Monday. And as usual, the portion about China contains little truth and many absurdities, exaggerations and fabrications. Expressive subjective element anchor :And as usual source : <writer> intensity : low … Objective speech event anchor :the entire 1st sentence source : <writer> implicit : true Expressive subjective element anchor :little truth source : <writer> intensity : medium … Direct subjective anchor :the entire 2nd sentence source : <writer> implicit :true intensity : high … Expressive subjective element anchor :many absurdities, exaggerations, and fabrications source : <writer> intensity : medium … ICWSM 2008

  39. (General) Subjectivity Types[Wilson 2008] Other (including cognitive) Note: similar ideas: polarity, semantic orientation, sentiment

  40. Extensions[Wilson 2008] I think people are happy because Chavez has fallen. direct subjective span: think source: <writer, I> attitude: direct subjective span: are happy source: <writer, I, People> attitude: inferred attitude span: are happy because Chavez has fallen type: neg sentiment intensity: medium target: attitude span: think type: positive arguing intensity: medium target: attitude span: are happy type: pos sentiment intensity: medium target: target span: people are happy because Chavez has fallen target span: Chavez has fallen target span: Chavez ICWSM 2008

  41. Layering with Other Annotation Schemes • E.g. Time, Lexical Semantics, Discourse… • Richer interpretations via combination • Potential disambiguation both ways • Example with the Penn Discourse Treebank (PDTB) Version 2 recently released through Language Data ConsortiumJoshi, Webber, Prasad, Miltsakaki, … http://www.seas.upenn.edu/~pdtb/ ICWSM 2008

  42. The class tag “COMPARISON” applies when the connective indicates that a discourse relation is established between Arg1 and Arg2 in order to highlight prominent differences between the two situations. ICWSM 2008

  43. In that suit, the SEC accused Mr. Antar of engaging in a "massive financial fraud" to overstate the earnings of Crazy Eddie, Edison, N.J., over a three-year period. Through his lawyers, Mr. Antar has denied allegations in the SEC suit and in civil suits previously filed by shareholders against Mr. Antar and others. ICWSM 2008

  44. PDTB [In that suit, the SEC accused Mr. Antar of engaging in a "massive financial fraud" to overstate the earnings of Crazy Eddie, Edison, N.J., over a three-year period. ARG1] IMPLICIT_CONTRAST[ Through his lawyers, Mr. Antar has denied allegations in the SEC suit and in civil suits previously filed by shareholders against Mr. Antar and others. ARG2] Contrast between the SEC accusing Mr. Antar of something, and his denying the accusation ICWSM 2008

  45. Subjectivity In that suit, the SEC [[accused SENTIMENT-NEG] Mr. Antar of engaging in a "massive financial fraud" to overstate the earnings of Crazy Eddie, Edison, N.J. ARGUING-POS], over a three-year period. Through his lawyers, Mr. Antar [has denied AGREE-NEG] allegations in the SEC suit and in civil suits previously filed by shareholders against Mr. Antar and others. Two attitudes combined into one large disagreement between two parties

  46. Subjectivity In that suit, the SEC [[accused SENTIMENT-NEG] Mr. Antar of engaging in a "massive financial fraud" to overstate the earnings of Crazy Eddie, Edison, N.J. ARGUING-POS], over a three-year period. Through his lawyers, Mr. Antar [has denied AGREE-NEG] allegations in the SEC suit and in civil suits previously filed by shareholders against Mr. Antar and others. Subjectivity: arguing-pos and agree-neg with different sources; Hypothesis: common with contrast. Help recognize the implicit contrast. ICWSM 2008

  47. Senses Word senses ICWSM 2008

  48. Senses ICWSM 2008

  49. Non-subjective senses of brilliant • Method for identifying brilliant material in paint - US Patent 7035464 • In a classic pasodoble, an opening section in the minor mode features a brilliant trumpet melody, while the second section in the relative major begins with the violins. ICWSM 2008

  50. Annotating WordNet senses • Assigning subjectivity labels toWordNet senses • S:subjective • positive • negative • O:objective • Why? Potential disambiguation both ways ICWSM 2008

More Related