HITS Colloquium Simone Ponzetto – Computational Approaches to Political Communication: From Populist Rhetoric to Moral Framing

by Simone Ponzetto, Universität Mannheim

Abstract

Recent years have seen a growing interest in the use of Natural Language Processing (NLP) methods for the analysis of political communication. While many computational approaches focus on topics, sentiment, or political stance, political discourse also conveys more subtle rhetorical, pragmatic, and moral dimensions that are central to democratic communication. In this talk, I present recent work on modelling such dimensions in parliamentary debates using theory-guided NLP approaches.

The presentation focuses on three lines of research. First, I discuss computational models for detecting references to “The People” and “The Elite” as core elements of populist rhetoric. Second, I present work on speech acts in parliamentary discourse, investigating how politicians use different communicative strategies such as cooperation, confrontation, criticism, or support. Third, I introduce a new framework for analysing moral framing in political debates, combining Moral Foundations Theory with fine-grained annotations of moral narratives and actor roles.

Across all three case studies, the talk highlights how transformer-based language models and linguistically informed annotation schemes can support the large-scale analysis of political discourse while preserving interpretability and theoretical grounding. More broadly, the presentation argues for closer connections between NLP, political text analysis, and communication science research on public discourse and democratic communication.

Short Bio

Simone Paolo Ponzetto is Full Professor of Information Systems at the University of Mannheim, Germany, where he is a member of the Data and Web Science Group and leads the Natural Language Processing and Information Retrieval Group. His research lies at the intersection of Natural Language Processing, Artificial Intelligence, and Computational Social Science, with a particular focus on knowledge acquisition, text understanding, multilingual NLP, and the application of NLP methods to research in the Digital Humanities and computational social sciences. Simone is a former Klaus Tschira Stiftung fellow (Stipendiat) and a former member of the NLP Group at EML Research. He looks forward to spending his sabbatical at HITS in Fall 2026 and to “coming back home” for this colloquium.

Registration

The talk will be hybrid.

If you would like to participate online, please register in advance here.

After registering, you will receive a confirmation email containing information about joining the meeting.

In case you are not able to attend, you can watch the talk afterwards on the HITS YouTube channel: https://www.youtube.com/user/TheHITSters.