Get out the vote: Determining support or opposition from Congressional floor-debate transcripts

By Matt Thomas, Bo Pang, Lillian Lee. 2006

651 citations recorded by the source corpus.

We investigate whether one can determine from the transcripts of U.S. Congressional floor debates whether the speeches represent support of or opposition to proposed legislation. To address this problem, we exploit the fact that these speeches occur as part of a discussion; this allows us to use sources of information regarding relationships between discourse segments, such as whether a given utterance indicates agreement with the opinion expressed by another. We find that the incorporation of such information yields substantial improvements over classifying speeches in isolation.

Subfields: Artificial Intelligence, Sociology and Political Science

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

In Sociology and Political Science

Citations in the corpus

Regularizing Text Categorization with Clusters of Words (2016, methodology): “Congressmen deciding “yea"/“nay" votes on the bill under discussion (Thomas et al., 2006)3 and product reviews from Amazon (Blitzer et al.”
Political Ideology Detection Using Recursive Neural Networks (2014, neutral): “The Convote dataset (Thomas et al., 2006) consists of US Congressional ﬂoor debate transcripts from 2005 in which all speakers have been labeled with their political party (Democrat, Republican, or independent).”
A survey on sentiment detection of reviews (2009, neutral): “There are mainly two different kinds of lexical filters used (Salvetti, Lewis, & Reichenbach, 2004): one based on hypernymy as provided by WordNet (Budanitsky & Hirst, 2001; Curran, 2002; Devitt & Vogel, 2004; Edmonds, 1999; Edmonds & Hirst, 2002; Fellbaum, 1998; Grefenstette, 1994; Justeson & Slava”
Classifying latent user attributes in twitter (2010, neutral): “Learning political orientation from congressional debate texts has been explored earlier, as in Thomas et al [14].”
Stance and Sentiment in Tweets (2016, background): “However, most work focuses on congressional debates [Thomas et al. 2006] or debates in online forums [Somasundaran and Wiebe 2010;”
Structured Models for Fine-to-Coarse Sentiment Analysis (2007, background): “…these systems have tackled the problem at different levels of granularity, from the document level (Pang et al., 2002), sentence level (Pang and Lee, 2004; Mao and Lebanon, 2006), phrase level (Tur-ney, 2002; Choi et al., 2005), as well as the speaker level in debates (Thomas et al., 2006).”
Stance Classification using Dialogic Properties of Persuasion (2012, methodology): “Other research classiﬁes the speaker’s side in a corpus of congressional ﬂoor debates (Thomas et al., 2006; Bansal et al., 2008; Balahur et al., 2009; Burfoot et al., 2011).”
News Verification by Exploiting Conflicting Social Viewpoints in Microblogs (2016, background): “Compared with traditional opinion mining methods(Kim and Hovy 2007; Park, Lee, and Song 2011; Thomas, Pang, and Lee 2006), our topic model is more focused on ﬁnding conﬂicting relations among tweets rather than their sentimental polarities.”
More than words: Social networks' text mining for consumer brand sentiments (2013, background): “Other studies investigating political sentiment analysis include studies by Efron (2004), Thomas et al. (2006), Park, Kim, and Barnett (2004) and Sobkowicz, Kaschesky, and Bouchard (Forthcoming).”
Making the Most of Bag of Words: Sentence Regularization with Alternating Direction Method of Multipliers (2014, neutral): “Congressmen alongside “yea”/“nay” votes on the bill under discussion (Thomas et al., 2006).”
Classifying Party Affiliation from Political Speech (2008, methodology): “SVMs and NB are also the most popular classification algorithms in current political text classification studies (Evans et al., 2005; Kwon et al., 2006; Thomas et al., 2006).”
A systematic analysis of performance measures for classification tasks (2009, methodology): “Additional performance measures other than the above are Accuracy used in Pang et al. (2002) and Thomas et al. (2006), or the correspondence between Precision and Recall in Gamon, Aue, Corston-Oliver, and Ringger (2005).”
A theory of learning from different domains (2010, background): “While movie reviews are the most commonly studied domain, sentiment analysis has been extended to a number of new domains, ranging from stock message boards to congressional floor debates (Das and Chen 2001; Thomas et al. 2006).”
Sentiment Analysis and Subjectivity (2010, background): “Sentiment classification is perhaps the most widely studied topic [3, 6, 8, 12, 13, 15, 16, 18, 27, 28, 33, 34, 35, 44, 45, 62, 64, 66, 67, 68, 70, 71, 73, 79, 80, 86, 92, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 111].”
Learning Sentiment Lexicons in Spanish (2012, background): “, 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.”
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.”