Next Article in Journal
Library Systems and Digital-Rights Management: Towards a Blockchain-Based Solution for Enhanced Privacy and Security
Previous Article in Journal
EHR Sampling Interval Bias Detection and Burden of Blood Pressure Excursions: Implications for Clinical Decision Support and Model Validity in Pediatric ECMO
Previous Article in Special Issue
An Architecture for Intelligent Tutoring in Virtual Reality: Integrating LLMs and Multimodal Interaction for Immersive Learning
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Information
Volume 17
Issue 2
10.3390/info17020136
information-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

The Ten Minutes That Shocked the World—Teaching Generative AI to Analyze the Trump–Zelensky Multimodal Debate

by
Isabella Poggi
1,*,
Tommaso Scaramella
2,
Sissy Violini
2,
Simona Careri
2,
Maria Désirée Epure
3,4 and
Daniele Dragoni
3,4
1
Department of Philosophy, Communication and Performing Arts, Roma Tre University, 00146 Rome, Italy
2
Independent Researcher, 00100 Rome, Italy
3
Department of Education, Roma Tre University, 00185 Rome, Italy
4
Department of Education, Cultural Heritage and Tourism, University of Macerata, 62100 Macerata, Italy
*
Author to whom correspondence should be addressed.
Information 2026, 17(2), 136; https://doi.org/10.3390/info17020136
Submission received: 17 December 2025 / Revised: 17 January 2026 / Accepted: 27 January 2026 / Published: 1 February 2026
(This article belongs to the Special Issue Interactive Learning: Human in the Loop System Design for Active Human–Computer Interactions)
Browse Figure
Versions Notes

Abstract

Today, foundation models simulate humans’ skills in translation, literature review, fact checking, fake-news detection, novel and poetry production. However, generative AI can also be applied to discourse analysis. This study instructed the Gemini 2.5 model to analyze multimodal political discourse. We selected some fragments from the Trump–Zelensky debate held at the White House on 28 February 2025 and annotated each sentence, gesture, intonation, gaze, and facial expression in terms of LEP (Logos, Ethos, Pathos) analysis to assess when speakers, in words or body communication, rely on rational argumentation, stress their own merits or the opponents’ demerits, or express and try to induce emotions in the audience. Through detailed prompts, we asked the Gemini 2.5 model to run the LEP analysis on the same fragments. Then, considering the human’s and model’s annotations in parallel, we proposed a metric to compare their respective analyses and measure discrepancies, finally tuning an optimized prompt for the model’s best performance, which in some cases outperformed the human’s analysis: an interesting application, since the LEP analysis highlights deep aspects of multimodal discourse but is highly time-consuming, while its automatic version allows us to interpret large chunks of speech in a fast but reliable way.
Keywords: multimodal discourse analysis; Logos, Ethos, Pathos; rhetorical analysis; generative AI; prompt engineering; political communication; political debate; Trump; Zelensky multimodal discourse analysis; Logos, Ethos, Pathos; rhetorical analysis; generative AI; prompt engineering; political communication; political debate; Trump; Zelensky
Graphical Abstract

Share and Cite

MDPI and ACS Style

Poggi, I.; Scaramella, T.; Violini, S.; Careri, S.; Epure, M.D.; Dragoni, D. The Ten Minutes That Shocked the World—Teaching Generative AI to Analyze the Trump–Zelensky Multimodal Debate. Information 2026, 17, 136. https://doi.org/10.3390/info17020136

AMA Style

Poggi I, Scaramella T, Violini S, Careri S, Epure MD, Dragoni D. The Ten Minutes That Shocked the World—Teaching Generative AI to Analyze the Trump–Zelensky Multimodal Debate. Information. 2026; 17(2):136. https://doi.org/10.3390/info17020136

Chicago/Turabian Style

Poggi, Isabella, Tommaso Scaramella, Sissy Violini, Simona Careri, Maria Désirée Epure, and Daniele Dragoni. 2026. "The Ten Minutes That Shocked the World—Teaching Generative AI to Analyze the Trump–Zelensky Multimodal Debate" Information 17, no. 2: 136. https://doi.org/10.3390/info17020136

APA Style

Poggi, I., Scaramella, T., Violini, S., Careri, S., Epure, M. D., & Dragoni, D. (2026). The Ten Minutes That Shocked the World—Teaching Generative AI to Analyze the Trump–Zelensky Multimodal Debate. Information, 17(2), 136. https://doi.org/10.3390/info17020136

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop