21 - 3/13/10 Sentiment Analysis 1 From William Cohen,...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
3/13/10 1 Sentiment Analysis 1 Manual and Automatic Subjectivity and Sentiment Analysis Jan Wiebe Josef Ruppenhofer Swapna Somasundaran University of Pittsburgh From William Cohen, originally from: EUROLAN SUMMER SCHOOL 2007, Semantics, Opinion and Sentiment in Text, July 23-August 3, University of Ia ş i, Romania http://www.cs.pitt.edu/~wiebe/tutorialsExtendedTalks.html
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
3/13/10 2 3 And an invited talk from Lillian Lee at ICWSM 2008 4 Some sentences expressing “opinion” or something a lot like opinion Wow , this is my 4th Olympus camera. – Most voters believe that he's not going to raise their taxes. - The United States fears a spill-over from the anti-terrorist campaign. - “We foresaw electoral fraud but not daylight robbery ,” Tsvangirai said.
Background image of page 2
3/13/10 3 5 Specific motivation: “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 denounced it. 6 More motivations 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? Etc .
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
3/13/10 4 7 More motivations 8
Background image of page 4
3/13/10 5 9 10
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
3/13/10 6 Some early work on opinion 12 ICWSM 2008 A source of information about semantic orientation: conjunction
Background image of page 6
3/13/10 7 13 ICWSM 2008 Hatzivassiloglou & McKeown 1997 1. Build training set: label all adj. with frequency > 20; test agreement with human annotators 2. Extract all conjoined adjectives nice and comfortable nice and scenic 14 ICWSM 2008 Hatzivassiloglou & McKeown 1997 3 . A supervised learning algorithm builds a graph of adjectives linked by the same or different semantic orientation nice handsome terrible comfortable painful expensive fun scenic
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
3/13/10 8 15 ICWSM 2008 Hatzivassiloglou & McKeown 1997 4. A clustering algorithm partitions the adjectives into two subsets nice handsome terrible comfortable painful expensive fun scenic slow + 16 Hatzivassiloglou & McKeown 1997 • Specifics: – 21M words of POS-tagged WSJ text
Background image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 26

21 - 3/13/10 Sentiment Analysis 1 From William Cohen,...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online