Political Ideology Detection Using Recursive Neural Networks

By Mohit Iyyer, Peter Enns, Jordan L. Boyd-Graber, Philip Resnik. 2014

329 citations recorded by the source corpus.

An individual’s words often reveal their political ideology. Existing automated techniques to identify ideology from text focus on bags of words or wordlists, ignoring syntax. Taking inspiration from recent work in sentiment analysis that successfully models the compositional aspect of language, we apply a recursive neural network (RNN) framework to the task of identifying the political position evinced by a sentence. To show the importance of modeling subsentential elements, we crowdsource political annotations at a phrase and sentence level. Our model outperforms existing models on our newly annotated dataset and an existing dataset.

Subfields: Artificial Intelligence, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

A Neural Network for Factoid Question Answering over Paragraphs (2014, methodology): “While a softmax layer over every node in the tree could predict answers (Socher et al., 2011; Iyyer et al., 2014), this method overlooks that most answers are themselves words (features) in other questions (e.g., a question on World War II might mention the Battle of the Bulge and vice versa).”
Convolutional Neural Networks for Sentence Classification (2014, methodology): “Initializing word vectors with those obtained from an unsupervised neural language model is a popular method to improve performance in the absence of a large supervised training set (Collobert et al., 2011; Socher et al., 2011; Iyyer et al., 2014).”
Deep Unordered Composition Rivals Syntactic Methods for Text Classification (2015, methodology): “Since acquiring labelled phrases is often expensive (Sayeed et al., 2012; Iyyer et al., 2014b), this result is promising for large or messy datasets where fine-grained annotation is infeasible.”
Automatically Neutralizing Subjective Bias in Text (2019, background): “• The Ideological Books Corpus (IBC) consisting of partisan books and magazine articles (Sim et al. 2013; Iyyer et al. 2014).”
Debiasing Word Embeddings from Sentiment Associations in Names (2020, background): “Another line of work aims to detect biased language in text directly using feature-based [12, 26] or neural-based approaches [13, 14].”
Time Waits for No One! Analysis and Challenges of Temporal Misalignment (2021, background): “This task can be useful for studies that involve an understanding of ideologies conveyed in text (Lin et al., 2008; Iyyer et al., 2014).”
In Plain Sight: Media Bias Through the Lens of Factual Reporting (2019, background): “] Trump lexical bias: bias stemming from content realization, or how things are said (Greene and Resnik, 2009; Hube and Fetahu, 2019; Iyyer et al., 2014; Recasens et al., 2013; Yano et al., 2010).”
A Transformer-based Framework for Neutralizing and Reversing the Political Polarity of News Articles (2021, methodology): “Existing methods either do not take into account context information by selecting words in fixed contexts [36, 67] or suffer limited modeling power on long sequence input [54] (RNN-based methods).”
A Transparent Framework for Evaluating Unintended Demographic Bias in Word Embeddings (2019, background): “…relevant in natural language systems such as, discriminatory gender bias (Bolukbasi et al., 2016a; Zhao et al., 2017), bias against regionally accented speech (Najaﬁan et al., 2016, 2017), personal or political view bias (Iyyer et al., 2014; Re-casens et al., 2013), and many other examples.”
Beyond Binary Labels: Political Ideology Prediction of Twitter Users (2017, background): “, 2013) or documents (Iyyer et al., 2014),”
Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media (2021, background): “diction, which is a well-established NLP task (e.g. Conover et al., 2011; Iyyer et al., 2014; Kannangara, 2018; Xiao et al., 2020).”
Can Large Language Models Transform Computational Social Science? (2023, methodology): “…political science through the detection of political leaning, ideology, and stance (Ahmed and Xing, 2010; Baly et al., 2020; Bamman and Smith, 2015; Iyyer et al., 2014; Johnson et al., 2017; Preoţiuc-Pietro et al., 2017; Luo et al., 2020a; Stefanov et al., 2020), as well as issue (Iyengar, 1990)…”
Understanding the Political Ideology of Legislators from Social Media Images (2019, background): “In more recent work, however, there are been greater interest in developing more general methods for measuring political ideology (Grimmer and Stewart, 2013, Iyyer et al., 2014, Sim et al., 2013, Slapin and Proksch, 2008).”
A Frame of Mind: Using Statistical Models for Detection of Framing and Agenda Setting Campaigns (2015, methodology): “, 2013) in order to measure ideological proportions in political speech, and (Iyyer et al., 2014) use recursive neural networks for a similar task.”
The Media Frames Corpus: Annotations of Frames Across Issues (2015, background): “Various models have been applied to news and social media datasets with the goal 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; Klebanov et al., 2010; Sim e”
Rotated Word Vector Representations and their Interpretability (2017, background): “The vectors also play a basic role as an embedding layer in deep learning models for NLP, affecting the expressive performance of the model (Iyyer et al., 2014; Tai et al., 2015; Yang et al., 2016).”
Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships (2016, methodology): “We hope to apply the RMN to nonﬁctional datasets as well; in this vein, Iyyer et al. (2014) apply a neural network to sentences from nonﬁction political books for ideology prediction.”
Discovering Biased News Articles Leveraging Multiple Human Annotations (2020, background): “…2005), how it is generated (Gentzkow and Shapiro, 2010) and others that detect it in diﬀerent domains (Cohen and Ruths, 2013; Recasens et al., 2013; Iyyer et al., 2014), related work lacks automatic solutions for the binary clas-siﬁcation task that classiﬁes mainstream news articles as Work…”