An unsupervised framework for tracing textual sources of moral change

TL;DR

This paper introduces an unsupervised NLP framework that traces and identifies textual sources influencing moral perception changes over time, applicable to social media and news data, especially during significant events like COVID-19.

Contribution

It presents a novel probabilistic topical approach to quantify moral change sources from text without supervision, advancing understanding of moral dynamics in social discourse.

Findings

Framework captures human moral judgments accurately.

Identifies coherent source topics linked to moral shifts.

Effective in analyzing real-time social events like COVID-19.

Abstract

Morality plays an important role in social well-being, but people's moral perception is not stable and changes over time. Recent advances in natural language processing have shown that text is an effective medium for informing moral change, but no attempt has been made to quantify the origins of these changes. We present a novel unsupervised framework for tracing textual sources of moral change toward entities through time. We characterize moral change with probabilistic topical distributions and infer the source text that exerts prominent influence on the moral time course. We evaluate our framework on a diverse set of data ranging from social media to news articles. We show that our framework not only captures fine-grained human moral judgments, but also identifies coherent source topics of moral change triggered by historical events. We apply our methodology to analyze the news in the COVID-19 pandemic and demonstrate its utility in identifying sources of moral change in high-impact and real-time social events.