Beyond Binary Labels: Political Ideology Prediction of Twitter Users

By Daniel Preotiuc-Pietro, Ye Liu, Daniel Hopkins, Lyle Ungar. 2017

282 citations recorded by the source corpus.

Automatic political orientation prediction from social media posts has to date proven successful only in distinguishing between publicly declared liberals and conservatives in the US. This study examines users’ political ideology using a seven-point scale which enables us to identify politically moderate and neutral users – groups which are of particular interest to political scientists and pollsters. Using a novel data set with political ideology labels self-reported through surveys, our goal is two-fold: a) to characterize the groups of politically engaged users through language use on Twitter; b) to build a fine-grained model that predicts political ideology of unseen users. Our results identify differences in both political leaning and engagement and the extent to which each group tweets using political keywords. Finally, we demonstrate how to improve ideology prediction accuracy by exploiting the relationships between the user groups.

Subfields: Communication, Political Science and International Relations, Sociology and Political Science, 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 Communication

In Political Science and International Relations

In Sociology and Political Science

In Natural Language Processing

Citations in the corpus

Ethical and social risks of harm from Language Models (2021, background): “Language utterances (e.g. tweets) are already being analysed to predict private information such as political orientation (Makazhanov et al., 2014; Preoţiuc-Pietro et al., 2017), age (Morgan-Lopez et al., 2017; Nguyen et al., 2013), and health data such as addiction relapses (Golbeck, 2018).”
Taxonomy of Risks posed by Language Models (2022, background): “Tweets) are already being analysed to predict private information such as political orientation [121, 144], age [131, 135], and health data such as addiction relapses [63].”
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models (2023, background): “Understanding Social Bias of LMs Studies have been conducted to measure political biases and predict the ideology of individual users (Colleoni et al., 2014; Makazhanov and Rafiei, 2013; Preoţiuc-Pietro et al., 2017), news articles (Li and Goldwasser, 2019; Feng et al.”
Diachronic degradation of language models: Insights from social media (2018, methodology): “This data was collected in a previous study by Preot¸iuc-Pietro et al. (2017) and is available online 3 .”
Can Large Language Models Transform Computational Social Science? (2023, background): “…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) and entity framing (van den Berg et al.,…”
Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey (2017, methodology): “According to previous studies, we present a taxonomy of current approaches topic models based on LDA model and in di ﬀ erent subject such as Social Network [76, 115-118], Software Engineering [8, 9, 25-26], Crime Science [119-121] and also in areas of Geographical [13, 14-17], Political Science [19-”