Which Side are You on? Identifying Perspectives at the Document and Sentence Levels

By Wei-Hao Lin, Theresa Wilson, Janyce Wiebe, Alexander G. Hauptmann. Conference on Computational Natural Language Learning, 2006

300 citations recorded by the source corpus.

In this paper we investigate a new problem of identifying the perspective from which a document is written. By perspective we mean a point of view, for example, from the perspective of Democrats or Republicans. Can computers learn to identify the perspective of a document? Not every sentence is written strongly from a perspective. Can computers learn to identify which sentences strongly convey a particular perspective? We develop statistical models to capture how perspectives are expressed at the document and sentence levels, and evaluate the proposed models on articles about the Israeli-Palestinian conflict. The results show that the proposed models successfully learn how perspectives are reflected in word usage and can identify the perspective of a document with high accuracy.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/7a2475703797fe51781ab43d10559f2bc306c796

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

Recognizing Stances in Ideological On-Line Debates (2010, background): “Generally, research in identifying political viewpoints has employed information from words in the document (Malouf and Mullen, 2008; Mullen and Malouf, 2006; Grefenstette et al., 2004; Laver et al., 2003; Martin and Vanberg, 2008; Lin et al., 2006; Lin, 2006).”
Latent Variable Models of Selectional Preference (2010, background): “Hierarchical Bayesian modelling has recently gained notable popularity in many core areas of natural language processing, from morphological segmentation (Goldwater et al., 2009) to opinion modelling (Lin et al., 2006).”
Author’s Sentiment Prediction (2020, background): “Many works have studied document-level sentiment analysis (Pang et al., 2002; Moraes et al., 2013; Lin et al., 2006; Tang et al., 2015).”
A survey on sentiment detection of reviews (2009, methodology): “In fact, most of the literatures showed that SVM and Naı̈ve Bayes are perfect methods in single domain document sentiment classification (Aue and Gamon, 2005; Beineke et al., 2004; Kennedy and Inkpen, 2006; Lin et al., 2006; Matsumoto et al., 2005; Mullen and Collier, 2004; Pang and Lee, 2004; Pang ”
Zero-Shot Stance Detection: A Dataset and Model Using Generalized Topic Representations (2020, methodology): “…topic-phrase deﬁnition with texts from online debate forums (Walker et al., 2012; Abbott et al., 2016; Hasan and Ng, 2014), information platforms (Lin et al., 2006; Murakami and Putra, 2010), student essays (Faulkner, 2014), news comments (Krejzl et al., 2017; Lozhnikov et al., 2018) and Twitter…”
Interactive Topic Modeling (2011, background): “…has been a thriving cottage industry adding more and more information to topic models to correct these shortcomings; either by modeling perspective (Paul and Girju, 2010; Lin et al., 2006), syntax (Wallach, 2006; Gruber et al., 2007), or author-ship (Rosen-Zvi et al., 2004; Dietz et al., 2007).”
Stance and Sentiment in Tweets (2016, methodology): “Lampos et al. 2013]. There are other subtasks in opinion mining related to stance classiﬁcation, such as biased language detection [Recasens et al. 2013; Yano et al. 2010], perspective identiﬁcation [Lin et al. 2006] and user classiﬁcation based on their views [Kato et al. 2008]. Perspective identiﬁ”
Discovering Biased News Articles Leveraging Multiple Human Annotations (2020, background): “…holder detection, or to identify direct and indirect reported speech (so that it is not attributed to the article author), etc. Political perspective detection is also studied on blogs (Lin et al., 2006; Ahmed and Xing, 2010) and news outlets (Baly et al., 2019; Patricia Aires et al., 2019).”
A Corpus for Research on Deliberation and Debate (2012, unknown): “…e.g. building on research in text classiﬁcation and topic modeling and applying it to both face-to-face and online debate and deliberation (Lin et al., 2006; Thomas et al., 2006; Somasundaran and Wiebe, 2009; Somasundaran and Wiebe, 2010; Bansal et al., 2008; Greene and Resnik, 2009;…”
A Study of Information Retrieval Weighting Schemes for Sentiment Analysis (2010, background): “Most of the work has focused on analyzing the content of movie or general product reviews, but there are also applications to other domains such as debates (Thomas et al., 2006; Lin et al., 2006), news (Devitt and Ahmad, 2007) and blogs (Ounis et al.”
The Hourglass of Emotions (2011, background): “[40] NB, SVM 2 Political articles None”
Computationally Detecting and Quantifying the Degree of Bias in Sentence-Level Text of News Stories (2015, unknown): “, [2]), casting the task as a two-way classification of the text as being either for/positive or against/negative (e.”
The Media Frames Corpus: Annotations of Frames Across Issues (2015, background): “…of identifying political ideology, or “perspective” (typically on a liberal to conservative scale) (Ahmed and Xing, 2010; Gentzkow and Shapiro, 2010; Lin et al., 2006; Hardisty et al., 2010; Kle- banov et al., 2010; Sim et al., 2013; Iyyer et al., 2014), or “stance” (position for or against an…”
Exploiting Social Network Structure for Person-to-Person Sentiment Analysis (2014, background): “…al., 2003; Mal-ouf and Mullen, 2008; Yu et al., 2008), bias (Yano et al., 2010; Recasens et al., 2013), and stance on debate topics (Thomas et al., 2006; Somasundaran and Wiebe, 2010; Lin et al., 2006; Anand et al., 2011), but these aspects of belief and social identity are not our primary concern.”
Stance Detection on Social Media: State of the Art and Trends (2020, background): “Consequently, the early work on stance detection was emerged in analyzing political debates in online forums [Lin et al. 2006; Somasundaran and Wiebe 2009; Murakami and Raymond 2010; Walker et al. 2012b].”