Just How Mad Are You? Finding Strong and Weak Opinion Clauses

By Theresa Wilson, Janyce Wiebe, Rebecca Hwa. AAAI Conference on Artificial Intelligence, 2004

499 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b419fb257870fe8024fb3f07dddd66328ae644cb

How researchers see this paper

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

1. Bing Liu
2. Erik Cambria
3. Richard Socher
4. B. Liu
5. Duyu Tang
6. Mohit Bansal
7. Soujanya Poria
8. Yejin Choi

Citations in the corpus

• Mining Opinions in Comparative Sentences (2008, background): “One major focus is sentiment classification and opinion mining (e.g., Pang et al 2002; Turney 2002; Hu and Liu 2004; Wilson et al 2004; Kim and Hovy 2004; Popescu and Etzioni 2005) © 2008.”
• Sentiment Classification using Automatically Extracted Subgraph Features (2010, methodology): “The difficulty with automatically deriving complex features comes with the increased feature space size.”
• Using appraisal groups for sentiment analysis (2005, background): “[22] have recently addressed learning models for finding opinion clauses and identifying their properties (mainly what we term force and orientation), based on clauses’ lexical and syntactic properties.”
• Sentiment Analysis and Subjectivity (2010, methodology): “Subsequent research also used other learning algorithms [35, 80, 103, 107].”
• SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining (2006, background): “…on its subject matter (Pang and Lee, 2004; Turney, 2002); 3. determining the strength of text PN-polarity, as in deciding e.g. whether the Positive opinion expressed by a text on its subject matter is Weakly Positive, Mildly Positive, or Strongly Positive (Pang and Lee, 2005; Wilson et al., 2004).”
• A Survey of Opinion Mining and Sentiment Analysis (2012, background): “It was pointed out in [109] that not only a single sentence may contain multiple opinions, but also both subjective and factual clauses.”
• A survey on sentiment detection of reviews (2009, unknown): “Many researchers think it is too coarse to compute a unit of an opinion for a whole document (Bai, Padman, & Airoldi, 2004; Bethard, Yu, Thornton, Hatzivassiloglou, & DanJurafsky, 2004; Bunescu & Mooney, 2004; Daille, 1996; Didier, 1995; Etzioni et al., 2004; Freitag & McCallum, 2000; Jacquemin & Bo”
• A Lexicon-based Approach for Hate Speech Detection (2015, background): “Besides identifying subjectivity and polarity of a sentence, [12] classify the strength of the opinions and emotions being expressed in individual clauses, considering clauses down to four levels deep.”
• FactBank: a corpus annotated with event factuality (2009, background): “Furthermore, opinions can be analyzed along different facets, such as the polarity of the attitude being expressed (i.e., positive vs. negative; e.g., Wilson et al. 2005), its rating (i.e., how much positively or negatively the target is evaluated as) (Pang and Lee 2005), and the expression strength”
• Determining the semantic orientation of terms through gloss classification (2005, background): “…the history of TC, topic-relatedness (aka thematic a.nity,or aboutness )has been the main dimension in terms of which TC has been studied, with categories representing topics and classi.ca­tion coinciding with the assignment to cj of those documents that were deemed to be about topic cj.”
• Combination of Domain Knowledge and Deep Learning for Sentiment Analysis (2017, background): “Research on this topic was conducted at different levels: term level [2], phrase level [3], sentence level [4] and document level [5,6].”
• A holistic lexicon-based approach to opinion mining (2008, background): “Note also that this model does not consider the strength of each opinion [33], i.”
• Identifying Sources of Opinions with Conditional Random Fields and Extraction Patterns (2005, methodology): “We view this problem as an information extraction task and adopt a hybrid approach that combines Conditional Random Fields (Lafferty et al., 2001) and a variation of AutoSlog (Riloff, 1996a).”
• Identifying comparative sentences in text documents (2006, background): “Other related works on sentiment classification and opinions discovery include [9, 15, 16, 23, 27, 33, 34, 35].”
• Learning Word Vectors for Sentiment Analysis (2011, methodology): “Thus, we extend the model with a supervised sentiment component that is capable of embracing many social and attitudinal aspects of meaning (Wilson et al., 2004; Alm et al., 2005; Andreevskaia and Bergler, 2006; Pang and Lee, 2005; Goldberg and Zhu, 2006; Snyder and Barzilay, 2007).”
• Text Mining in Big Data Analytics (2020, methodology): “Determining the extent of text polarity to categorize the positive opinion extended by a text on its subject matter as weakly positive, mildly positive, or strongly positive [21,22].”