Fightin' Words: Lexical Feature Selection and Evaluation for Identifying the Content of Political Conflict

Monroe, Burt L.; Colaresi, Michael P.; Quinn, Kevin M.

doi:10.1093/pan/mpn018

Cited by 411 publications

(274 citation statements)

References 35 publications

Supporting

Mentioning

269

Contrasting

Unclassified

Order By: Relevance

“…For instance, the pronouns "he" and "she" emerge as highly discriminant words, with Poisson scaling parameter estimates of β = −.54 and β = −1.68 respectively. This is similar to the results of Monroe, Quinn and Colaresi (2008) who found that uncorrected partisan association measures for female pronouns (of the kind that the Poisson scaling model uses) indicated that they were Democrat words. …”

supporting

confidence: 88%

Validating Estimates of Latent Traits from Textual Data Using Human Judgment as a Benchmark

Lowe¹,

Benoit

2013

Polit. anal.

View full text Add to dashboard Cite

Automated and statistical methods for estimating latent political traits and classes from textual data hold great promise, since virtually every political act involves the production of text. Statistical models of natural language features, however, are heavily laden with unrealistic assumptions about the process that generates this data, including the stochastic process of text generation, the functional link between political variables and observed text, and the nature of the variables (and dimensions) on which observed text should be conditioned. While acknowledging statistical models of latent traits to be "wrong", political scientists nonetheless treat the treat their results as sufficiently valid to be useful. In this paper, we address the issue of substantive validity in the face of potential model failure, in the context of unsupervised scaling methods of latent traits. We critically examine one popular parametric measurement model of latent traits for text and then compare its results to systematic human judgments of the texts as a benchmark for validity. * This research was supported by the European Research Council grant ERC-2011-StG 283794-QUANTESS. Will Lowe is at MZES, University of Mannheim and Kenneth Benoit is at the Department of Methodology, London School of Economics and the Department of Political Science, Trinity College Dublin. 1A vast amount of effort in political science focuses on estimating characteristics of political actors-parties, legislators, candidates, voters, and so on-that may be estimated, but never directly observed. Whether we call them "ideal points", policy preferences, topics, or issue emphases, these latent traits and latent classes are not only fundamentally unobservable, but also exist in a dimensional space that is fundamentally unknowable. 1 This has hardly prevented political researchers from attempting to identify and estimate such quantities, however, and a variety of such methods are widely used. Many, such as the analysis of roll call votes, suffer from problems of data censorship and selection that produce biased estimates of the quantities desired. Not all actors vote, co-sponsor bills, or return our questionnaires, but there is one activity that always accompanies political action: speech.This simple fact, coupled with a revolution in the availability of vast quantities of recorded text and speech, has spurred the development of a wide range of methods for analyzing textual data, most of which are surveyed in Grimmer and Stewart (Forthcoming).Every statistical model applied to data-textual or otherwise-requires assumptions.As Grimmer and Stewart (Forthcoming) point out, such assumptions are always wrong.For textual data, these assumptions concern: the process that generates the observed textual data, including the stochastic process of text generation; the functional model linking political variables of interest and observed text; and the nature of the variables (and dimensions) on which observed text should be conditioned. The reality is that the wh...

show abstract

supporting

confidence: 88%

Validating Estimates of Latent Traits from Textual Data Using Human Judgment as a Benchmark

Lowe¹,

Benoit

2013

Polit. anal.

View full text Add to dashboard Cite

show abstract

“…Politicians may compete over the meaning and hence the political frame of a given issue, indicating that the framing is an important part of politics (Entman 1993). We use the concept of framing in a way similar to that of Monroe et al (2008). Words that are more specific to an individual political party, given the agenda of the speech, will contribute to a higher degree of framing.…”

Section: Strategies Of Mainstream Parties To Handle Challenger Partiesmentioning

confidence: 99%

Voices from the far right: a text analysis of Swedish parliamentary debates

Magnusson¹,

Öhrvall²,

Barrling³

et al. 2018

Preprint

View full text Add to dashboard Cite

In this paper we study the effects of a radical right party entering a national parliament, on the parliament discourse. We follow the classification developed by Meguid (2008) and use a probabilistic topic model approach to analyze the 300,000 speeches delivered in the Swedish parliament between 1994 and 2017. Our results indicate that immigration became a more prevalent topic in party leader debates when the Sweden Democrats entered the parliament in 2010. The other parties started to address immigration more, but still not to the extent that the Sweden Democrats did. In 2015, as Sweden faced a migration crisis, immigration became a more salient issue in the parliamentary debates. This could be seen as an external shock that forced the mainstream parties to put more emphasis on the topic of immigration. We conclude that the mainstream parties used a partly dismissive, partly adversarial strategy in their speeches when the SD entered the parliament. The migration crises in 2015 made them focus more on immigration and they thereby adopted a more adversarial strategy.

show abstract

“…See Table 5 for the ten most important words for each category of this variable using methods developed by [57] and described in detail below.…”

Section: Disappearancementioning

confidence: 99%

“…See Table 6 for the ten most important words for each category of this variable using methods developed by [57] and described in detail below. Freedom of Assembly and Association: This variable measuring freedom of assembly and association is coded 0 when the rights to freedom of assembly or association were severely restricted or denied completely to all citizens; a score of 1 indicates that these rights were limited for all citizens or severely restricted or denied for select groups; and a score of 2 indicates that these rights were virtually unrestricted and freely enjoyed by practically all citizens in a given year.…”

Section: Disappearancementioning

confidence: 99%

Human Rights Texts: Converting Human Rights Primary Source Documents into Data

et al. 2015

View full text Add to dashboard Cite

We introduce and make publicly available a large corpus of digitized primary source human rights documents which are published annually by monitoring agencies that include Amnesty International, Human Rights Watch, the Lawyers Committee for Human Rights, and the United States Department of State. In addition to the digitized text, we also make available and describe document-term matrices, which are datasets that systematically organize the word counts from each unique document by each unique term within the corpus of human rights documents. To contextualize the importance of this corpus, we describe the development of coding procedures in the human rights community and several existing categorical indicators that have been created by human coding of the human rights documents contained in the corpus. We then discuss how the new human rights corpus and the existing human rights datasets can be used with a variety of statistical analyses and machine learning algorithms to help scholars understand how human rights practices and reporting have evolved over time. We close with a discussion of our plans for dataset maintenance, updating, and availability.

show abstract

Fightin' Words: Lexical Feature Selection and Evaluation for Identifying the Content of Political Conflict

Cited by 411 publications

References 35 publications

Validating Estimates of Latent Traits from Textual Data Using Human Judgment as a Benchmark

Validating Estimates of Latent Traits from Textual Data Using Human Judgment as a Benchmark

Voices from the far right: a text analysis of Swedish parliamentary debates

Human Rights Texts: Converting Human Rights Primary Source Documents into Data

Contact Info

Product

Resources

About