Learning Subjective Language

By Janyce Wiebe, Theresa Wilson, Rebecca F. Bruce, Matthew Bell, Melanie J. Martin. International Conference on Computational Logic, 2004

824 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/ce20678cfbffded477f43df156f6ab37f6edc6a0

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

1. B. Liu
2. Noah A. Smith
3. Mohit Bansal
4. Bing Liu
5. Yejin Choi
6. Saif M. Mohammad
7. Erik Cambria
8. Jianfeng Gao

Citations in the corpus

• Current State of Text Sentiment Analysis from Opinion to Emotion Mining (2017, background): “Some previous works focus on comparing the effectiveness of adjectives, adverbs, verbs, and nouns in the classification task, including Benamara et al. [2007], Nasukawa and Yi [2003], and Wiebe et al. [2004].”
• Political Ideology Detection Using Recursive Neural Networks (2014, background): “Wiebe et al. (2004) show that low-frequency words and some collocations are a good indicators of subjectivity.”
• Opinion Word Expansion and Target Extraction through Double Propagation (2011, methodology): “Wiebe (2000) and Wiebe et al. (2004) proposed an approach to finding subjective adjectives using the results of word clustering according to their distributional similarity.”
• Exploring Visual Engagement Signals for Representation Learning (2021, background): “The resulting textual descriptions depart from the exactly what it says on the tin approach of standard image captioning tasks and express private states [65, 82]: opinions, emotions, and speculations, for example.”
• A Survey of Opinion Mining and Sentiment Analysis (2012, background): “The task of classifying a sentence as subjective or objective is often called subjectivity classification in the existing literature [30, 87, 88, 106, 109, 110, 113].”
• Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations (2021, background): “Detecting emotions from language has been a significant area of research in NLP for the past two decades (Liscombe et al., 2003; Aman and Szpakowicz, 2007; Desmet and Hoste, 2013; Hirschberg and Manning, 2015; Poria et al., 2019).”
• A survey on sentiment detection of reviews (2009, background): “…has been performed and proposed for discriminating between subjective and objective text at the document and sentence levels (Bruce & Wiebe, 1999; Finn, Kushmerick, & Smyth, 2002; Hatzivassiloglou & Wiebe, 2000; Wiebe, 2000; Wiebe et al., 1999; Wiebe et al., 2002; Yu & Hatzivassiloglou, 2003).”
• Annotating Expressions of Opinions and Emotions in Language (2005, methodology): “In addition to Appraisal Theory, subjectivity annotation of text in context has also been performed in Yu and Hatzivassiloglou (2003), Bruce and Wiebe (1999), and Wiebe et al. (2004) .”
• Language-Aware Truth Assessment of Fact Candidates (2014, methodology): “Literature on sentiment analysis (Turney et al., 2002; Liu et al., 2005), subjectivity detection (Riloff and Wiebe, 2003; Wiebe et al., 2004), and bias detection (Yu and Hatzivassiloglou, 2003; Recasens et al., 2013) has developed lexicons for identifying subjective language.”
• Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences (2003, methodology): “…opinion detection has been performed by Wiebe and colleagues (Bruce and Wiebe, 1999; Wiebe et al., 1999; Hatzivassiloglou and Wiebe, 2000; Wiebe, 2000; Wiebe et al., 2002), who proposed methods for discriminating between subjective and objective text at the document, sentence, and phrase levels.”
• The Validity of Sentiment Analysis: Comparing Manual Annotation, Crowd-Coding, Dictionary Approaches, and Machine Learning Algorithms (2021, background): “Sentiment is generally expressed with ambiguous and creative language (Liu, 2012; Pang & Lee, 2008; Wiebe et al., 2004).”
• Semi-Supervised Recognition of Sarcasm in Twitter and Amazon (2010, background): “Modeling the underlying patterns of sarcastic utterances is interesting from the psychological and cognitive perspectives and can benefit various NLP systems such as review summarization (Popescu and Etzioni, 2005; Pang and Lee, 2004; Wiebe et al., 2004; Hu and Liu, 2004) and dialogue systems.”
• Lexicon-Based Methods for Sentiment Analysis (2011, methodology): “based work makes use of linguistic features for training (Riloff and Wiebe 2003; Mullen and Collier 2004; Wiebe et al. 2004; Kennedy and Inkpen 2006; Ng, Dasgupta, and Niaz Arifin 2006; Sokolova and Lapalme 2008), it nonetheless still suffers from lack of”
• Subjective Natural Language Problems: Motivations, Applications, Characterizations, and Implications (2011, background): “Language analysts, including computational linguists, have long acknowledged the importance of such topics (B¨uhler, 1934; Lyons, 1977; Jakobson, 1996; Halli-day, 1996; Wiebe et al, 2004; Wilson et al, 2005).”
• ICWSM - A Great Catchy Name: Semi-Supervised Recognition of Sarcastic Sentences in Online Product Reviews (2010, background): “Another important benefit is the improvement of review summarization and opinion mining systems such as (Popescu and Etzioni 2005; Pang and Lee 2004; Wiebe et al. 2004; Hu and Liu 2004; Kessler and Nicolov 2009), currently incapable of dealing with sarcastic sentences.”