1. 1 I am here… Lu Chen Kno.e.sis Center Amit Sheth Wright State University advisor of has PhD student is in director of

2. Extracting What We Think and How We Feel from What We Say in Social Media ---- Subjective Information Extraction Subjective Information Extraction, Lu Chen 2 Lu Chen Kno.e.sis Center Wright State University http://cdryan.com/blog/think-feel/

3. Subjectivity refers to the subject and his or her perspective, feelings, beliefs, and desires. in philosophy, the term is usually contrasted with objectivity. [1] Subjective Information Extraction, Lu Chen 3 [1] Block, Ned; Flanagan, Owen J.; & Gzeldere, Gven (Eds.) The Nature of Consciousness: Philosophical Debates. Cambridge, MA: MIT Press. http://fineartamerica.com/featured/its-all-subjective-john-crowther.html Extraction of subjective information: Extracting structured subjective information from unstructured content Allowing computation to be done on “what people think” and “how people feel”

4. Directions From coarse-grained to fine-grained –Document level -> sentence level -> expression level –General sentiment -> domain-dependent sentiment -> target-dependent sentiment –Sentiment  Subjective information Sentiment (positive/negative/neutral) -> emotion (happy, sad, angry, surprise, etc.) Other types of subjective information: Intent, suggestion/recommendation, wish/expectation, outlook, viewpoint, etc. From static to dynamic –Our attitude can be changed during social communication. Modeling, detecting, and tracking the change of attitude What leads to the change of attitude? E.g., persuasion campaign Subjective Information Extraction, Lu Chen 4 static dynamic coarse-grained fine-grained subjective information

5. Subjective Information Extraction, Lu Chen 5 Jan, 2012 Aug, 2011May, 2012 Discovering Fine- grained Sentiment in Suicide Notes Extracting Sentiment Expressions from Twitter Electoral Prediction Understanding and Modeling Emotions with Tweets Progress

6. Subjective Information Extraction, Lu Chen 6 Extracting a diverse and richer set of sentiment-bearing expressions, including formal and slang words/phrases Assessing the target-dependent polarity of each sentiment expression A novel formulation of assigning polarity to a sentiment expression as a constrained optimization problem over the tweet corpus Extracting Diverse Sentiment Expressions With Target-dependent Polarity from Twitter Lu Chen, Wenbo Wang, Meenakshi Nagarajan, Shaojun Wang, and Amit P. Sheth

7. Challenges Sentiment expressions in tweets can be very diverse. Subjective Information Extraction, Lu Chen 7 Quantitative Study of 3000 Tweets: Distributions of N-grams and Part-of-speech of the Sentiment Expressions

8. Challenges The polarity of a sentiment expression is sensitive to its target. Subjective Information Extraction, Lu Chen 8 predictable predictable movie predictable stock long long river long battery life long time for downloading

9. Approach Subjective Information Extraction, Lu Chen 9 Extracting Candidate Expressions Identifying Inter-Expression Relations Assessing Target-dependent Polarity

10. Extracting Candidate Expressions Root word: a word that is considered sentiment-bearing in general sense. Collecting root words from –General-purpose sentiment lexicons: MPQA, General Inquirer, and SentiWordNet –Slang dictionary: Urban Dictionary For each tweet, selecting the “on-target” root words, and extracting all the n-grams that contain at least one selected root word as candidates Subjective Information Extraction, Lu Chen 10

11. Identifying Inter-Expression Relations Connecting the candidate expressions via two types of inter- expression relations – consistency relation and inconsistency relation Basic ideas: –A sentiment expression is inconsistent with its negation; two sentiment expressions linked by contrasting conjunctions are likely to be inconsistent. –Two adjacent expressions are consistent if they do not overlap, and there is no extra negation applied to them or no contrasting conjunction connecting them. Subjective Information Extraction, Lu Chen 11

12. An Example 1.I saw The Avengers yesterday evening. It was long but it was very good! 2.I do enjoy The Avengers, but it's both overrated and problematic. 3.Saw the avengers last night. Mad overrated. Cheesy lines and horrible writing. Very predictable. 4.The avengers was good but the plot was just simple minded and predictable. 5.The Avengers was good. I was not disappointed. Subjective Information Extraction, Lu Chen 12

13. Assessing Target-dependent Polarity For each candidate expression, –P-Probability – the probability that indicates positive sentiment –N-Probability – the probability that indicates negative sentiment For each pair of candidate expressions and, –Consistency probability – the probability that and have the same polarity: –Inconsistency probability – the probability that and have different polarities: Subjective Information Extraction, Lu Chen 13

14. An Optimization Model We want the consistency and inconsistency probabilities derived from the the P-Probabilities and N-Probabilities of the candidates will be closest to their expectations suggested by the relation networks. Objective Function: Subjective Information Extraction, Lu Chen 14 where and are the weights of the edges (the frequency of the relations) between and in the consistency and inconsistency relation networks, and n is the total number of candidate expressions.

15. The Example Subjective Information Extraction, Lu Chen 15

16. Evaluation Datasets: –168,005 tweets about movies –258,655 tweets about persons Gold standard: –1,500 tweets labeled with sentiment expressions and overall polarities for the movie targets –1,500 tweets labeled with sentiment expressions and overall polarities for the person targets Baseline methods: –MPQA, GI, SWN: For each extracted root word regarding the target, simply look up its polarity in MPQA, General Inquirer and SentiWordNet, respectively. –PROP: a propagation approach proposed by Qiu et al. (2009) –COM-const: Assign 0.5 to all the candidates as their initial P-Probabilities. –COM-gelex: Initialize the candidates’ polarities according to the root word set. Subjective Information Extraction, Lu Chen 16 Reference: Qiu, G.; Liu, B.; Bu, J.; and Chen, C. 2009. Expanding domain sentiment lexicon through double propagation. In Proc. of IJCAI.

17. Subjective Information Extraction, Lu Chen 17

18. Subjective Information Extraction, Lu Chen 18

19. Application Subjective Information Extraction, Lu Chen 19

20. Subjective Information Extraction, Lu Chen 20 Relevance of User Groups Based on Demographics and Participation to Social Media Based Prediction -- -- A Case Study of 2012 U.S. Republican Presidential Primaries Lu Chen, Wenbo Wang, and Amit P. Sheth Existing studies on predicting election result are under the assumption that all the users should be treated equally. How could different groups of users be different in predicting election results? 1. Providing a detailed analysis of the social media users on different dimensions 2. Estimating the “vote” of each user by analyzing his/her tweets, and predicted the results based on “vote-counting” 3. Examining the predictive power of different user groups in predicting the results of Super Tuesday races in 10 states

21. User Categorization Subjective Information Extraction, Lu Chen 21 Engagement Degree Tweet Mode Content Type Political Preference Location

22. Electoral Prediction with Different User Groups Subjective Information Extraction, Lu Chen 22 Revealing the challenge of identifying the vote intent of “silent majority” Retweets may not necessarily reflect users' attitude. Prediction of user’s vote based on more opinion tweets is not necessarily more accurate than the prediction using more information tweets The right-leaning user group provides the most accurate prediction result. In the best case (56-day time window), it correctly predict the winners in 8 out of 10 states with an average prediction error of 0.1. To some extent, it demonstrates the importance of identifying likely voters in electoral prediction.

23. Emotion Discovering Fine-grained Sentiment in Suicide Notes: Classify each sentence from suicide notes into 15 emotional categories, e.g., love, pride, guilt, blame, hopelessness, etc. Emotion Identification from Twitter Data: 7 emotion categories, including joy, sadness, anger, lover, fear, thankfulness, and surprise –Can we automatically create a large emotion dataset with high quality labels from Twitter? How? –What features can effectively improve the performance of supervised machine learning algorithms? –How much performance will be gained by increasing the size of the training data? –Can the system developed on Twitter data be directly applied to identify emotions from other datasets? Subjective Information Extraction, Lu Chen 23

24. What’s next? Subjective Information Extraction, Lu Chen 24 static dynamic coarse-grained fine-grained subjective information Detecting the change of attitude during persuasive communication Discriminating other types of subjective information from sentiment, e.g., wish, intent

25. Thank you ! Subjective Information Extraction, Lu Chen 25