Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences

By Hong Yu, Vasileios Hatzivassiloglou. Conference on Empirical Methods in Natural Language Processing, 2003

1,261 citations recorded by the source corpus.

Opinion question answering is a challenging task for natural language processing. In this paper, we discuss a necessary component for an opinion question answering system: separating opinions from fact, at both the document and sentence level. We present a Bayesian classifier for discriminating between documents with a preponderance of opinions such as editorials from regular news stories, and describe three unsupervised, statistical techniques for the significantly harder task of detecting opinions at the sentence level. We also present a first model for classifying opinion sentences as positive or negative in terms of the main perspective being expressed in the opinion. Results from a large collection of news stories and a human evaluation of 400 sentences are reported, indicating that we achieve very high performance in document classification (upwards of 97% precision and recall), and respectable performance in detecting opinions and classifying them at the sentence level as positive, negative, or neutral (up to 91% accuracy).

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/3f46b61a7216e5763ffab5d33e06b88c9d490c85

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Determining Term Subjectivity and Term Orientation for Opinion Mining (2006, background): “However, we think this approach lacks realism since it is also true that, for the very same languages, there is no available lexical resource where terms are tagged as having either a Subjective or an Objective connotation.”
Which Side are You on? Identifying Perspectives at the Document and Sentence Levels (2006, background): “, 2003), identifying opinionated documents (Yu and Hatzivassiloglou, 2003) and sentences (Yu and Hatzivassiloglou, 2003; Riloff et al.”
Creating Subjective and Objective Sentence Classifiers from Unannotated Texts (2005, methodology): “We also added features for the following parts of speech, which were shown to be effective in previous work [5, 15, 11]: pronouns, modals (excluding ‘will’), adjectives, cardinal numbers, and adverbs (excluding ‘not’).”
Enhanced Sentiment Learning Using Twitter Hashtags and Smileys (2010, background): “While most of the works on sentiment analysis focus on full text, some works address sentiment analysis in the phrasal and sentence level, see (Yu and Hatzivassiloglou, 2003; Wilson et al., 2005; McDonald et al., 2007; Titov and McDon-ald, 2008a; Titov and McDonald, 2008b; Wilson et al., 2009; Tsur…”
Evidence on the Information Content of Text in Analyst Reports (2014, background): “…extract opinion in a wide variety of text domains, including manager opinions in financial statements (Li 2010), investor sentiments in Internet stock message boards (Das and Chen 2007; Antweiler and Frank 2004), and editorial opinions in Wall Street Journal articles (Yu and Hatzivassiloglou 2003).”
Automatic Identification of Sentiment Vocabulary: Exploiting Low Association with Known Sentiment Terms (2005, background): “Yu and Hatzivassiloglou (2003) extend this approach by (1) applying it at the sentence level (instead of the document-level), (2) taking into account non-adjectival parts-of-speech, and (3) using larger sets of seed words.”
Cyber Hate Classification: 'Othering' Language And Paragraph Embedding (2018, methodology): “According to [49], while part-of-speech tagging does not significantly improve classifier performance, we apply POS tagging for extracting specific content (verbs, nouns and adjectives) for lexicon building.”
Learning Subjective Language (2004, methodology): “Yu and Hatzivassiloglou (2003) perform opinion text classification.”
Articles: Recognizing Contextual Polarity: An Exploration of Features for Phrase-Level Sentiment Analysis (2009, background): “Morinaga et al. (2002), Yu and Hatzivassiloglou (2003), Kim and Hovy (2004), Hu and Liu (2004), and Grefenstette et al. (2004) 11 all begin by ﬁrst creating prior-polarity lexicons.”
Word Sense and Subjectivity (2006, methodology): “2These distinctions are not strictly needed for this paper, but may help the reader appreciate the examples given below. and question answering (e.g., (Yu and Hatzivassiloglou, 2003; Stoyanov et al., 2005)).”
Determining the Sentiment of Opinions (2004, background): “We wish to study opinion in general; our work most closely resembles that of (Yu and Hatzivassiloglou 2003).”
Learning Sentiment Lexicons in Spanish (2012, background): “…et al., 2005), tracking sentiment timelines in on-line forums and news (Lloyd et al., 2005; Balog et al., 2006), analysis of political debates (Thomas et al., 2006; Carvalho et al., 2011), question answering (Yu and Hatzivassiloglou, 2003), and conversation summarization (Carenini et al., 2008).”
Automatically Assessing Review Helpfulness (2006, background): “Yu and Hatzivassiloglou (2003) identified the polarity of opinion sentences using semantically oriented words.”
SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining (2006, methodology): “This amounts to performing binary text categorization under categories Subjective and Objective (Pang and Lee, 2004; Yu and Hatzivassiloglou, 2003); 2. determining text PN-polarity, as in deciding if a given Subjective text expresses a Positive or a Negative opinion on its subject matter (Pang and…”
Determining the semantic orientation of terms through gloss classification (2005, background): “…Experimentation Keywords Opinion Mining, Text Classi.cation, Semantic Orientation, Sentiment Classi.cation, Polarity Detection Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or…”