High Risk of Political Bias in Black Box Emotion Inference Models

TL;DR

This study reveals significant political bias in emotion inference models used for sentiment analysis, demonstrating how biases in training data can skew social science research outcomes and proposing mitigation strategies.

Contribution

The paper provides a bias audit of a Polish sentiment analysis model, highlighting political bias propagation and testing dataset pruning as a mitigation method.

Findings

Bias in model predictions linked to political affiliations

Human annotations propagate political biases

Pruning training data reduces but does not eliminate bias

Abstract

This paper investigates the presence of political bias in emotion inference models used for sentiment analysis (SA) in social science research. Machine learning models often reflect biases in their training data, impacting the validity of their outcomes. While previous research has highlighted gender and race biases, our study focuses on political bias - an underexplored yet pervasive issue that can skew the interpretation of text data across a wide array of studies. We conducted a bias audit on a Polish sentiment analysis model developed in our lab. By analyzing valence predictions for names and sentences involving Polish politicians, we uncovered systematic differences influenced by political affiliations. Our findings indicate that annotations by human raters propagate political biases into the model's predictions. To mitigate this, we pruned the training dataset of texts mentioning these politicians and observed a reduction in bias, though not its complete elimination. Given the significant implications of political bias in SA, our study emphasizes caution in employing these models for social science research. We recommend a critical examination of SA results and propose using lexicon-based systems as a more ideologically neutral alternative. This paper underscores the necessity for ongoing scrutiny and methodological adjustments to ensure the reliability and impartiality of the use of machine learning in academic and applied contexts.