Corpus ID: 52154541

"Read My Lips": Using Automatic Text Analysis to Classify Politicians by Party and Ideology

  title={"Read My Lips": Using Automatic Text Analysis to Classify Politicians by Party and Ideology},
  author={Eitan Sapiro-Gheiler},
The increasing digitization of political speech has opened the door to studying a new dimension of political behavior using text analysis. [...] Key Method Applying machine learning techniques, we use this data to automatically classify senators according to party, obtaining accuracy in the 70-95% range depending on the specific method used. We also show that using text to predict DW-NOMINATE scores, a common proxy for ideology, does not improve upon these already-successful results. This classification…Expand
Slanted Frames Predicting Partisanship from Video Data
We use machine learning to predict partisanship based on video data. Using a dataset of video frames from over 2,000 televised political ads, we train a convolutional neural network to predict theExpand
The Formal Understanding Models
It is found that the machine formal information processing and the human content information processing are opposite in convergence, and the combination of the three formalized understanding models and the bilingual model of interpretative translation is the key to formal understanding, intelligent understanding and social understanding. Expand
How to Understand Three Types of Cognitive Models
Not only the three types of cognitive systems, such as quasi-holographic space, five-loop traversal and order-sequence structure, all of them are difficult to understand, now are easily understood, and a new cognitive paradigm that is simplified is obtained. Expand


Extracting Policy Positions from Political Texts Using Words as Data
We present a new way of extracting policy positions from political texts that treats texts not as discourses to be understood and interpreted but rather, as data in the form of words. We compare thisExpand
A Scaling Model for Estimating Time-Series Party Positions from Texts
A scaling algorithm called WORDFISH to estimate policy positions based on word frequencies in texts is proposed and it is found that words with strong political connotations are the best discriminators between parties. Expand
Measuring Political Positions from Legislative Speech
Existing approaches to measuring political disagreement from text data perform poorly except when applied to narrowly selected texts discussing the same issues and written in the same style. WeExpand
How to Analyze Political Attention with Minimal Assumptions and Costs
Previous methods of analyzing the substance of political attention have had to make several restrictive assumptions or been prohibitively costly when applied to large-scale political texts. Here, weExpand
Measuring Polarization in High-Dimensional Data: Method and Application to Congressional Speech
This paper studies trends in the partisanship of Congressional speech from 1873 to 2009. It defines partisanship to be the ease with which an observer could infer a congressperson’s party from aExpand
Off the Record: Unrecorded Legislative Votes, Selection Bias and Roll-Call Vote Analysis
Scholars often use roll-call votes to study legislative behaviour. However, many legislatures only conclude a minority of decisions by roll call. Thus, if these votes are not a random sample of theExpand
Mandates and Policy Outputs: U.S. Party Platforms and Federal Expenditures
Political parties in the United States are usually regarded as too weak and decentralized, too much the prey of office-seeking politicians and special interests, to function effectively asExpand
Measuring How Political Parties Keep Their Promises: A Positive Perspective from Political Science
This chapter addresses three questions about the relationship between political discourse and action: Do political parties keep their promises once elected? What are the methodologies used byExpand
Political Parties and Public Policy: Social Welfare Policy from Carter to Bush
Recent studies have concluded that the U.S. system of separation of powers is surprisingly effective in producing legislation, even under conditions of divided government. This article goes beyondExpand
Efficient Estimation of Word Representations in Vector Space
Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities. Expand