--- title: "Recognizing Contextual Polarity in — Wilson 2005" description: "Sentiment lexicons usually record a word's prior polarity, meaning how it reads out of context." authors: ["Theresa Wilson", "Janyce Wiebe", "Paul Hoffmann"] year: 2005 venue: "Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing" source: "https://aclanthology.org/H05-1044/" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/wilson-2005-recognizing-contextual-polarity-phrase-level/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wilson-2005-recognizing-contextual-polarity-phrase-level/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2005](https://md.research.elamur.ai/free/en/papers/2005/) / Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis # Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis **Authors:** [Theresa Wilson](https://md.research.elamur.ai/free/en/authors/theresa-wilson/), [Janyce Wiebe](https://md.research.elamur.ai/free/en/authors/janyce-wiebe/), [Paul Hoffmann](https://md.research.elamur.ai/free/en/authors/paul-hoffmann/) · **Year:** 2005 · **Venue:** Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/) **Links:** [Publisher's page](https://aclanthology.org/H05-1044/) · [PDF](https://aclanthology.org/H05-1044.pdf) · [OpenAlex](https://openalex.org/W2022204871) **Citations:** 3345 citations (openalex-snapshot · 2026-10-14) · [634](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary Sentiment lexicons usually record a word's prior polarity, meaning how it reads out of context. Inside a real sentence, though, the word's effect can be reversed, cancelled, or made neutral. Negation, irrealis modality, word sense, syntactic role and diminishers all play a part. This paper addresses automatic recognition of this contextual polarity at the phrase level. The authors extended the MPQA Opinion Corpus by going through the subjective expressions it already marks and assigning each one a contextual polarity of positive, negative, neutral or both. They validated this scheme with a two-annotator agreement study. They also built a lexicon of over 8,000 single-word subjectivity clues, each tagged with prior polarity and reliability. Each clue occurrence is then classified in two machine-learned steps. The first separates neutral from polar instances. The second decides the polarity of the polar ones. In 10-fold cross-validation, the system significantly outperforms a baseline that relies on prior polarity alone, and it covers a large share of sentiment expressions. This matters for opinion question answering, summarization and review mining, which need sentiment pinned to individual expressions rather than whole documents. ## Key points - **Annotation scheme:** contextual polarity was added to the subjective expressions of the MPQA Opinion Corpus. In total, 15,991 expressions in 425 documents (8,984 sentences) were labelled positive, negative, both or neutral. Annotators judged the polarity conveyed after the whole sentence is interpreted. - **Agreement:** on 10 documents with 447 expressions, the two annotators agreed 82% of the time (κ = 0.72). When cases marked uncertain (18%) are dropped, agreement rises to 90% (κ = 0.84). - **Corpus statistics:** 47% of sentences contain two or more subjective expressions. Among those, 17% mix positive and negative expressions, and 62% mix polar and neutral ones. This supports analysis below the sentence level. - **Data split:** a development set of 66 documents (2,808 expressions) was used for exploration and feature design. The remaining 359 documents (13,183 expressions) were used for 10-fold cross-validation. - **Lexicon:** the lexicon starts from the Riloff and Wiebe clues and is expanded with a dictionary, a thesaurus and the General Inquirer lists. Each clue is tagged strongsubj or weaksubj. Prior polarities are 59.7% negative, 33.1% positive, 0.3% both and 6.9% neutral. - **Ablation:** dropping individual groups of polarity features changed results significantly in only one case, neutral F-measure when the modification features were removed. Reaching significance over baseline required the combination of features. ## Interesting ideas - **Split the decision into two stages.** Separate "is this sentiment at all?" from "which direction?". Most lexicon hits are actually neutral in context, so filtering them first keeps the polarity step from being swamped. This design transfers to stance or emotion tagging in other languages. - **Derive token labels from span annotations with explicit merge rules.** For example, a clue inside both a positive and a negative span becomes "both", while a negative-plus-neutral overlap becomes negative. This lets existing span-level corpora train word-level classifiers without new annotation. - **Let annotators flag uncertainty.** Agreement can then be reported both with and without borderline cases. This shows whether disagreement comes from the guidelines or from genuinely ambiguous items, which is useful for any new annotation project, such as Ukrainian sentiment data. - **Keep neutral-prior words in a sentiment lexicon.** Verbs like *feel* or *look* and intensifiers like *deeply* carry no polarity themselves but signal that sentiment is nearby. Including them raises coverage at little cost. - **Use a prior-polarity-only classifier as the baseline, then ablate feature groups.** Comparing against the lexicon alone, and then removing groups of features, shows exactly how much context modelling adds. It also shows whether any single feature family is doing the work, which is a cheap, interpretable evaluation pattern. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/) ## Cited by Cited by 634 papers of our library cite it (of the 140884 whose bibliographies we read); 50 of them have a page here, 584 not yet. - [Sentiment Analysis of Twitter Data](https://md.research.elamur.ai/free/en/papers/agarwal-2011-sentiment-analysis-twitter-data/) - [Robust Sentiment Detection on Twitter from Biased and Noisy Data](https://md.research.elamur.ai/free/en/papers/barbosa-2010-robust-sentiment-detection-twitter-biased/) - [Acquired TASTE: Multimodal Stance Detection with Textual and Structural Embeddings](https://md.research.elamur.ai/free/en/papers/barel-2025-acquired-taste-multimodal-stance-detection/) - [Better Document-level Sentiment Analysis from RST Discourse Parsing](https://md.research.elamur.ai/free/en/papers/bhatia-2015-better-document-level-sentiment-analysis/) - [Aggregated Word Pair Features for Implicit Discourse Relation Disambiguation](https://md.research.elamur.ai/free/en/papers/biran-2013-aggregated-word-pair-features-implicit/) - [Comparing Word Representations for Implicit Discourse Relation Classification](https://md.research.elamur.ai/free/en/papers/braud-2015-comparing-word-representations-implicit-discourse/) - [Learning Connective-based Word Representations for Implicit Discourse Relation Identification](https://md.research.elamur.ai/free/en/papers/braud-2016-learning-connective-based-word-representations/) - [Enhanced Sentiment Learning Using Twitter Hashtags and Smileys](https://md.research.elamur.ai/free/en/papers/davidov-2010-enhanced-sentiment-learning-twitter-hashtags/) - [Joint Inference and Disambiguation of Implicit Sentiments via Implicature Constraints](https://md.research.elamur.ai/free/en/papers/deng-2014-joint-inference-disambiguation-implicit-sentiments/) - [Sentiment Propagation via Implicature Constraints](https://md.research.elamur.ai/free/en/papers/deng-2014-sentiment-propagation-implicature-constraints/) - [Automatic sense prediction for implicit discourse relations in text](https://md.research.elamur.ai/free/en/papers/disc-2009-pitler-automatic-sense-prediction-implicit-discourse/) - [The Role of Pragmatic and Discourse Context in Determining Argument Impact](https://md.research.elamur.ai/free/en/papers/durmus-2019-role-pragmatic-discourse-context-determining/) - [Sarcasm Analysis Using Conversation Context](https://md.research.elamur.ai/free/en/papers/ghosh-2018-sarcasm-analysis-conversation-context/) - [Interpreting Verbal Irony: Linguistic Strategies and the Connection to the Type of Semantic Incongruity](https://md.research.elamur.ai/free/en/papers/ghosh-2020-interpreting-verbal-irony-linguistic-strategies/) - [X-PuDu at SemEval-2022 Task 6: Multilingual Learning for English and Arabic Sarcasm Detection](https://md.research.elamur.ai/free/en/papers/han-2022-x-pudu-semeval-2022-task/) - [A Retrospective Analysis of the Fake News Challenge Stance-Detection Task](https://md.research.elamur.ai/free/en/papers/hanselowski-2018-retrospective-analysis-fake-news-challenge/) - [Monday mornings are my fave :) #not Exploring the Automatic Recognition of Irony in English tweets](https://md.research.elamur.ai/free/en/papers/hee-2016-monday-mornings-are-my-fave/) - [We Usually Don't Like Going to the Dentist: Using Common Sense to Detect Irony on Twitter](https://md.research.elamur.ai/free/en/papers/hee-2018-we-usually-don-t-like/) - [Toward Controlled Generation of Text](https://md.research.elamur.ai/free/en/papers/hu-2017-toward-controlled-generation-text/) - [Political Ideology Detection Using Recursive Neural Networks](https://md.research.elamur.ai/free/en/papers/iyyer-2014-political-ideology-detection-recursive-neural/) - [Extracting Opinions, Opinion Holders, and Topics Expressed in Online News Media Text](https://md.research.elamur.ai/free/en/papers/kim-2006-extracting-opinions-opinion-holders-topics/) - [NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews](https://md.research.elamur.ai/free/en/papers/kiritchenko-2014-nrc-canada-2014-detecting-aspects/) - [Unsupervised stance detection for arguments from consequences](https://md.research.elamur.ai/free/en/papers/kobbe-2020-unsupervised-stance-detection-arguments-consequences/) - [Argument Mining: A Survey](https://md.research.elamur.ai/free/en/papers/lawrence-2019-argument-mining-survey/) - [Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings](https://md.research.elamur.ai/free/en/papers/liu-2015-fine-grained-opinion-mining-recurrent/) - [A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict](https://md.research.elamur.ai/free/en/papers/liu-2022-dual-channel-framework-sarcasm-recognition/) - [POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection](https://md.research.elamur.ai/free/en/papers/liu-2022-politics-pretraining-same-story-article/) - [Learning Multilingual Subjective Language via Cross-Lingual Projections](https://md.research.elamur.ai/free/en/papers/mihalcea-2007-learning-multilingual-subjective-language-cross/) - [Open Domain Targeted Sentiment](https://md.research.elamur.ai/free/en/papers/mitchell-2013-open-domain-targeted-sentiment/) - [NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2013-nrc-canada-building-state-art/) - [SemEval-2016 Task 6: Detecting Stance in Tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2016-semeval-2016-task-6-detecting/) - [Emotion Intensities in Tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2017-emotion-intensities-tweets/) - [WASSA-2017 Shared Task on Emotion Intensity](https://md.research.elamur.ai/free/en/papers/mohammad-2017-wassa-2017-shared-task-emotion/) - [Twitter as a Corpus for Sentiment Analysis and Opinion Mining](https://md.research.elamur.ai/free/en/papers/pak-2010-twitter-as-corpus-sentiment-analysis/) - [Improving Implicit Discourse Relation Recognition Through Feature Set Optimization](https://md.research.elamur.ai/free/en/papers/park-2012-improving-implicit-discourse-relation-recognition/) - [Sarcasm as Contrast between a Positive Sentiment and Negative Situation](https://md.research.elamur.ai/free/en/papers/prag-2013-riloff-sarcasm-as-contrast-between-positive/) - [Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge](https://md.research.elamur.ai/free/en/papers/rahman-2012-resolving-complex-cases-definite-pronouns/) - [Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking](https://md.research.elamur.ai/free/en/papers/rashkin-2017-truth-varying-shades-analyzing-language/) - [SemEval-2015 Task 10: Sentiment Analysis in Twitter](https://md.research.elamur.ai/free/en/papers/rosenthal-2015-semeval-2015-task-10-sentiment/) - [Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions](https://md.research.elamur.ai/free/en/papers/socher-2011-semi-supervised-recursive-autoencoders-predicting/) - [Scare Quotes as Markers of “Questionable” Word Usages and Misalignment in Conversation: An Annotation Study](https://md.research.elamur.ai/free/en/papers/soler-2026-scare-quotes-as-markers-questionable/) - [Supervised and Unsupervised Methods in Employing Discourse Relations for Improving Opinion Polarity Classification](https://md.research.elamur.ai/free/en/papers/somasundaran-2009-supervised-unsupervised-methods-employing-discourse/) - [Recognizing Stances in Ideological On-Line Debates](https://md.research.elamur.ai/free/en/papers/somasundaran-2010-recognizing-stances-ideological-line-debates/) - [UniTN End-to-End Discourse Parser for CoNLL 2016 Shared Task](https://md.research.elamur.ai/free/en/papers/stepanov-2016-unitn-end-end-discourse-parser/) - [Lexicon-Based Methods for Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/taboada-2011-lexicon-based-methods-sentiment-analysis/) - [Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification](https://md.research.elamur.ai/free/en/papers/tang-2014-learning-sentiment-specific-word-embedding/) - [Automated Fact Checking: Task Formulations, Methods and Future Directions](https://md.research.elamur.ai/free/en/papers/thorne-2018-automated-fact-checking-task-formulations/) - [Co-Training for Cross-Lingual Sentiment Classification](https://md.research.elamur.ai/free/en/papers/wan-2009-co-training-cross-lingual-sentiment/) - [Implicit Discourse Relation Recognition by Selecting Typical Training Examples](https://md.research.elamur.ai/free/en/papers/wang-2012-implicit-discourse-relation-recognition-selecting/) - [Recognizing Contextual Polarity: An Exploration of Features for Phrase-Level Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wilson-2009-recognizing-contextual-polarity-exploration-features/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{wilson2005recognizing, title = {{Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis}}, author = {Wilson, Theresa and Wiebe, Janyce and Hoffmann, Paul}, booktitle = {Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing}, year = {2005}, doi = {10.3115/1220575.1220619}, url = {https://doi.org/10.3115/1220575.1220619} } ``` - [← previous Recognising Textual Entailment with Logical Inference](https://md.research.elamur.ai/free/en/papers/bos-2005-recognising-textual-entailment-logical-inference/) - [next → Representing Discourse Coherence: A Corpus-Based Study](https://md.research.elamur.ai/free/en/papers/wolf-2005-representing-discourse-coherence-corpus-based/) - [↑ back to papers of 2005](https://md.research.elamur.ai/free/en/papers/2005/) ## References 21 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. P. Beineke, T. Hastie, and S. Vaithyanathan. 2004. The sentimental factor: Improving review classification via human-provided information. In ACL-2004. [find](https://scholar.google.com/scholar?q=P%2E+Beineke%2C+T%2E+Hastie%2C+and+S%2E+Vaithyanathan%2E+2004%2E+The+sentimental+factor%3A+Improving+review+classification+via+human%2Dprovided+information%2E+In+ACL%2D2004%2E) 2. M. Collins. 1997. Three generative, lexicalised models for statistical parsing. In ACL-1997. [find](https://scholar.google.com/scholar?q=M%2E+Collins%2E+1997%2E+Three+generative%2C+lexicalised+models+for+statistical+parsing%2E+In+ACL%2D1997%2E) [our card](https://md.research.elamur.ai/free/en/papers/collins-1997-three-generative-lexicalised-models-statistical/) 3. K. Dave, S. Lawrence, and D. M. Pennock. 2003. Mining the peanut gallery: Opinion extraction and semantic classification of product reviews. In WWW-2003. [find](https://scholar.google.com/scholar?q=K%2E+Dave%2C+S%2E+Lawrence%2C+and+D%2E+M%2E+Pennock%2E+2003%2E+Mining+the+peanut+gallery%3A+Opinion+extraction+and+semantic+classification+of+product+reviews%2E+In+WWW%2D2003%2E) 4. The General-Inquirer. 2000. [http://www.wjh.harvard.edu/˜inquirer/spreadsheet](http://www.wjh.harvard.edu/˜inquirer/spreadsheet) guide.htm. [↗](http://www.wjh.harvard.edu/˜inquirer/spreadsheet) 5. G. Grefenstette, Y. Qu, J.G. Shanahan, and D.A. Evans. 2001. Coupling niche browsers and affect analysis for an opinion mining application. In RIAO-2004. [find](https://scholar.google.com/scholar?q=G%2E+Grefenstette%2C+Y%2E+Qu%2C+J%2EG%2E+Shanahan%2C+and+D%2EA%2E+Evans%2E+2001%2E+Coupling+niche+browsers+and+affect+analysis+for+an+opinion+mining+application%2E+In+RIAO%2D2004%2E) 6. V. Hatzivassiloglou and K. McKeown. 1997. Predicting the semantic orientation of adjectives. In ACL-1997. [find](https://scholar.google.com/scholar?q=V%2E+Hatzivassiloglou+and+K%2E+McKeown%2E+1997%2E+Predicting+the+semantic+orientation+of+adjectives%2E+In+ACL%2D1997%2E) 7. M. Hu and B. Liu. 2004. Mining and summarizing customer reviews. In KDD-2004. [find](https://scholar.google.com/scholar?q=M%2E+Hu+and+B%2E+Liu%2E+2004%2E+Mining+and+summarizing+customer+reviews%2E+In+KDD%2D2004%2E) 8. J. Kamps and M. Marx. 2002. Words with attitude. In 1st International WordNet Conference. [find](https://scholar.google.com/scholar?q=J%2E+Kamps+and+M%2E+Marx%2E+2002%2E+Words+with+attitude%2E+In+1st+International+WordNet+Conference%2E) 9. S-M. Kim and E. Hovy. 2004. Determining the sentiment of opinions. In Coling 2004. [find](https://scholar.google.com/scholar?q=S%2DM%2E+Kim+and+E%2E+Hovy%2E+2004%2E+Determining+the+sentiment+of+opinions%2E+In+Coling+2004%2E) [our card](https://md.research.elamur.ai/free/en/papers/kim-2004-determining-sentiment-opinions/) 10. T. Nasukawa and J. Yi. 2003. Sentiment analysis: Capturing favorability using natural language processing. In K-CAP 2003. [find](https://scholar.google.com/scholar?q=T%2E+Nasukawa+and+J%2E+Yi%2E+2003%2E+Sentiment+analysis%3A+Capturing+favorability+using+natural+language+processing%2E+In+K%2DCAP+2003%2E) 11. B. Pang and L. Lee. 2004. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In ACL-2004. [find](https://scholar.google.com/scholar?q=B%2E+Pang+and+L%2E+Lee%2E+2004%2E+A+sentimental+education%3A+Sentiment+analysis+using+subjectivity+summarization+based+on+minimum+cuts%2E+In+ACL%2D2004%2E) [our card](https://md.research.elamur.ai/free/en/papers/pang-2004-sentimental-education-sentiment-analysis-subjectivity/) 12. L. Polanya and A. Zaenen. 2004. Contextual valence shifters. In Working Notes — Exploring Attitude and Affect in Text (AAAI Spring Symposium Series). [find](https://scholar.google.com/scholar?q=L%2E+Polanya+and+A%2E+Zaenen%2E+2004%2E+Contextual+valence+shifters%2E+In+Working+Notes+%E2%80%94+Exploring+Attitude+and+Affect+in+Text+%28AAAI+Spring+Symposium+Series%29%2E) 13. R. Quirk, S. Greenbaum, G. Leech, and J. Svartvik. 1985. A Comprehensive Grammar of the English Language. Longman, New York. [find](https://scholar.google.com/scholar?q=R%2E+Quirk%2C+S%2E+Greenbaum%2C+G%2E+Leech%2C+and+J%2E+Svartvik%2E+1985%2E+A+Comprehensive+Grammar+of+the+English+Language%2E+Longman%2C+New+York%2E) 14. E. Riloff and J. Wiebe. 2003. Learning extraction patterns for subjective expressions. In EMNLP-2003. [find](https://scholar.google.com/scholar?q=E%2E+Riloff+and+J%2E+Wiebe%2E+2003%2E+Learning+extraction+patterns+for+subjective+expressions%2E+In+EMNLP%2D2003%2E) [our card](https://md.research.elamur.ai/free/en/papers/riloff-2003-learning-extraction-patterns-subjective-expressions/) 15. R. E. Schapire and Y. Singer. 2000. BoosTexter: A boosting-based system for text categorization. Machine Learning, 39(2/3):135–168. [find](https://scholar.google.com/scholar?q=R%2E+E%2E+Schapire+and+Y%2E+Singer%2E+2000%2E+BoosTexter%3A+A+boosting%2Dbased+system+for+text+categorization%2E+Machine+Learning%2C+39%282%2F3%29%3A135%E2%80%93168%2E) 16. P. Turney. 2002. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In ACL-2002. [find](https://scholar.google.com/scholar?q=P%2E+Turney%2E+2002%2E+Thumbs+up+or+thumbs+down%3F+Semantic+orientation+applied+to+unsupervised+classification+of+reviews%2E+In+ACL%2D2002%2E) [our card](https://md.research.elamur.ai/free/en/papers/turney-2002-thumbs-up-or-thumbs-down/) 17. J. Wiebe and E. Riloff. 2005. Creating subjective and objective sentence classifiers from unannotated texts. In CICLing-2005. [find](https://scholar.google.com/scholar?q=J%2E+Wiebe+and+E%2E+Riloff%2E+2005%2E+Creating+subjective+and+objective+sentence+classifiers+from+unannotated+texts%2E+In+CICLing%2D2005%2E) 18. J. Wiebe, T. Wilson, and C. Cardie. 2005. Annotating expressions of opinions and emotions in language. Language Resources and Evalution (formerly Computers and the Humanities), 1(2). [find](https://scholar.google.com/scholar?q=J%2E+Wiebe%2C+T%2E+Wilson%2C+and+C%2E+Cardie%2E+2005%2E+Annotating+expressions+of+opinions+and+emotions+in+language%2E+Language+Resources+and+Evalution+%28formerly+Computers+and+the+Humanities%29%2C+1%282%29%2E) 19. F. Xia and M. Palmer. 2001. Converting dependency structures to phrase structures. In HLT-2001. [find](https://scholar.google.com/scholar?q=F%2E+Xia+and+M%2E+Palmer%2E+2001%2E+Converting+dependency+structures+to+phrase+structures%2E+In+HLT%2D2001%2E) 20. J. Yi, T. Nasukawa, R. Bunescu, and W. Niblack. 2003. Sentiment analyzer: Extracting sentiments about a given topic using natural language processing techniques. In IEEE ICDM-2003. [find](https://scholar.google.com/scholar?q=J%2E+Yi%2C+T%2E+Nasukawa%2C+R%2E+Bunescu%2C+and+W%2E+Niblack%2E+2003%2E+Sentiment+analyzer%3A+Extracting+sentiments+about+a+given+topic+using+natural+language+processing+techniques%2E+In+IEEE+ICDM%2D2003%2E) 21. H. Yu and V. Hatzivassiloglou. 2003. Towards answering opinion questions: Separating facts from opinions and identifying the polarity of opinion sentences. In EMNLP-2003. [find](https://scholar.google.com/scholar?q=H%2E+Yu+and+V%2E+Hatzivassiloglou%2E+2003%2E+Towards+answering+opinion+questions%3A+Separating+facts+from+opinions+and+identifying+the+polarity+of+opinion+sentences%2E+In+EMNLP%2D2003%2E) [our card](https://md.research.elamur.ai/free/en/papers/yu-2003-answering-opinion-questions-separating-facts/)