Tea Party in the House: A Hierarchical Ideal Point Topic Model and Its Application to Republican Legislators in the 112th Congress

Nguyen, Viet-An; Boyd-Graber, Jordan; Resnik, Philip; Miler, Kristina C.

doi:10.3115/v1/p15-1139

Cited by 48 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Type of learning Examples Classification Supervised • understand audience sentiment from social media • sort party manifestos into predefined categories on the ideological spectrum • understand US Supreme Court decisions (Evans et al, 2007), • extract party affiliation (Yu et al, 2008) • preferences for foreign aid (Baker, 2015) • ideological mapping of candidates and campaign contributors (Bonica, 2014) • extraction of text features from documents (Uysal, 2016;Nguyen et al, 2015) These political text-as-data applications are related to the broader field of NLP, which is concerned with the interactions between computers and human or natural languages (rather than formal languages). After the 1980s and alongside the developments in machine learning and advances in hardware and technology, NLP has mostly evolved around the use of statistical models to automatically identify patterns and structures in language, through the analysis of large sets of annotated texts or corpora.…”

Section: Methodsmentioning

confidence: 99%

“…Feature extraction is a type of dimensionality reduction task and can be accomplished using either semi-supervised or unsupervised learning. Selection and extraction of text features from documents or words is essential for text mining and information retrieval, where learning is done by seeking to reduce the dimension of the learning set into a set of features (Uysal, 2016;Nguyen et al, 2015).…”

Section: Ai: Machine Learning and Nlpmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Political Science

Chatsiou¹,

Mikhaylov

2020

The SAGE Handbook of Research Methods in Political Science and International Relations

View full text Add to dashboard Cite

IntroductionPolitical science, and social science in general, have traditionally been using computational methods to study areas such as voting behavior, policy making, international conflict, and international development. More recently, increasingly available quantities of data are being combined with improved algorithms and affordable computational resources to predict, learn, and discover new insights from data that is large in volume and variety. New developments in the areas of machine learning, deep learning, natural language processing (NLP), and, more generally, artificial intelligence (AI) are opening up new opportunities for testing theories and evaluating the impact of interventions and programs in a more dynamic and effective way.Applications using large volumes of structured and unstructured data are becoming common in government and industry, and increasingly also in social science research.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Ai: Machine Learning and Nlpmentioning

confidence: 99%

Deep Learning for Political Science

Chatsiou¹,

Mikhaylov

2020

The SAGE Handbook of Research Methods in Political Science and International Relations

View full text Add to dashboard Cite

show abstract

“…Combining political psychology and machine learning, topic modeling has been applied to the House of Representatives floor speeches to measure member personality traits (Ramey et al 2016). Hierarchical topic modeling was applied to look at how the Tea Party Republicans relate with regards to their ideal points to the remaining of the Republican representatives in Congress (Nguyen et al 2015). A similar hierarchical modeling approach was used to analyze the political priorities emphasized in US Senate press statements (Grimmer 2010).…”

Section: Structural Topic Modelingmentioning

confidence: 99%

Migration Policy Framing in Political Discourse: Evidence from Canada and the USA

Hajdinjak

Morris

Amos

2019

Computational Social Sciences

View full text Add to dashboard Cite

How do parties discuss migration policy in legislative speeches? Legislative bodies are an arena for verbal conflicts where the parties vie for their ideological interests but also sharpen new rhetorical figures. Political parties develop policy stances strategically different from those of competing parties and elucidate those stances through legislative debates and public statements. A large body of literature argues that some issues, like migration, fall in a gap between established societal cleavages over which parties do not have robust, issue-specific ownership. More recent research suggests migration may be a part of a new transnational cleavage that pits cosmopolitan sensibilities against nationalist sentiments in a conflict over issue ownership and policy framing. Building off this debate, we hypothesize that parties discuss migration topics by diverting attention to subcomponents of migration policy over which they have established issue ownership. Using machine learning techniques, we test this assertion by measuring the differences in salience and framing of migration-related topics over time in the debates of the lower houses of Canada and the United States-the Canadian House of Commons and the United States' House of Representatives from 1994 to 2016. We find that there are substantive differences in the emphasis on and framing of the migration policy between the two ideological blocks. Democrats in the USA and liberals in Canada emphasize subcomponents of the migration debate which they traditionally own, such as welfare and humanitarian aspects. Both conservative blocks do the same by framing their discussion of migration through a focus on security and legalistic aspect of migration. However, due to strong polarization in the USA, the differences in the emphasis on the issues traditionally owned by the two ideological camps are stronger in the USA than in Canada.

show abstract

“…Researchers study the public voting record of lawmakers and model the probability of each vote, which is usually described as the interaction of the lawmaker's ideal point and the position of the bill. Along this line of research, computer science researchers extend the ideal point model to a variety of aspects, including applying Ideology @RepSamFarr @repdonnaedwards @PeterWelch @HillaryClinton @latimes @YahooNews @washingtonpost @MSNBC @BarackObama @CBSNews @ProPublica @WSJ @cspan @Newsweek @npr @ABC @politico @HuffingtonPost @USATODAY @ForeignPolicy @Forbes @CNN @CNBC @time @usnews @realDonaldTrump @FoxNews @WashTimes @RandPaul @Newsmax_Media @RepTrentFranks @SteveScalise natural language processing and topic modeling techniques on bills [7,8,12,14,19].…”

Section: Ideology Detection In Roll Call Voting Datamentioning

confidence: 99%

Ideology Detection for Twitter Users via Link Analysis

Chen

Sun

et al. 2017

Social, Cultural, and Behavioral Modeling

View full text Add to dashboard Cite

The problem of ideology detection is to study the latent (political) placement for people, which is traditionally studied on politicians according to their voting behaviors. Recently, more and more studies begin to address the ideology detection problem for ordinary users based on their online behaviors that can be captured by social media, e.g., Twitter. As far as we are concerned, however, the vast majority of the existing methods on ideology detection on social media have oversimplified the problem as a binary classification problem (i.e., liberal vs. conservative). Moreover, though social links can play a critical role in deciding one's ideology, most of the existing work ignores the heterogeneous types of links in social media. In this paper we propose to detect numerical ideology positions for Twitter users, according to their follow, mention, and retweet links to a selected set of politicians. A unified probabilistic model is proposed that can (1) explain the reasons why links are built among people in terms of their ideology, (2) integrate heterogeneous types of links together in determining people's ideology, and (3) automatically learn the quality of each type of links in deciding one's ideology. Experiments have demonstrated the advantages of our model in terms of both ranking and political leaning classification accuracy. It is shown that (1) using multiple types of links is better than using any single type of links alone to determine one's ideology, and (2) our model is even more superior than baselines when dealing with people that are sparsely linked in one type of links. We also show that the detected ideology for Twitter users aligns with our intuition quite well.

show abstract

Tea Party in the House: A Hierarchical Ideal Point Topic Model and Its Application to Republican Legislators in the 112th Congress

Cited by 48 publications

References 27 publications

Deep Learning for Political Science

Deep Learning for Political Science

Migration Policy Framing in Political Discourse: Evidence from Canada and the USA

Ideology Detection for Twitter Users via Link Analysis

Contact Info

Product

Resources

About