Learning Moral Diversity: Modelling Individual Perspectives in Moral Classification of Texts
2026-06-22 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied how people’s different opinions affect understanding moral values in social media posts, like tweets. Instead of combining all people's answers into one answer, they made a model that learns what each person thinks individually. This helps the model better predict each person's opinion and shows why people disagree. They found that disagreements are natural and important, and ignoring them can give a false sense of accuracy. Their method helps better capture the variety of moral views in text.
moral valuessocial media textnatural language processingannotator disagreementpretrained language modelsubjectivitycrowdsourcingclassificationtweet analysismachine learning models
Authors
Yi Ren, Lewis Mitchell, Matthew Roughan
Abstract
Understanding moral values in social media text offers insight into moral judgement formation, and supervised NLP models trained on crowdsourced data have achieved strong classification performance. However, most approaches simplify the problem by aggregating multiple annotators' labels into a single "ground truth", overlooking the inherent subjectivity of the task. In practice, there are disagreements between annotators caused by personal viewpoint or inherent ambiguities, particularly for short tweets. Here, we extend a pretrained language model with a layer that learns annotator-specific features. Our model improves predictions of individual annotations and yields representations that reveal meaningful insights into annotators' moral perspectives. We show that models trained on aggregated labels may hide variation and give a misleading impression of performance. Overall, we demonstrate that disagreement reflects the inherent subjectivity of the task and that modelling individual perspectives creates benefits for moral classification of texts.