An unsupervised framework for tracing textual sources of moral change
This work addresses the challenge of understanding moral dynamics in society, which is important for social scientists and policymakers, though it is incremental in applying existing NLP techniques to a new problem.
The authors tackled the problem of quantifying the origins of moral change over time by developing an unsupervised framework that traces textual sources influencing moral perceptions toward entities. They demonstrated its effectiveness on diverse datasets, including social media and news, showing it captures human moral judgments and identifies coherent source topics triggered by historical events, with an application to COVID-19 news.
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.