MuSe2025: The 6th Multimodal Sentiment Analysis Workshop Dublin Royal Convention Centre Dublin, Ireland, October 27-31, 2025

The Multimodal Sentiment Analysis Workshop (MuSe) 2025 is dedicated to multimodal signal processing, sentiment and emotion recognition. The workshop provides a stimulating environment for developing and evaluating novel approaches to multimedia processing and deep learning methods for automatic audiovisual, textual, and physiological affect modeling. The workshop is intended to appeal to avariety of research communities, encouraging synergies between different disciplines. Mainly, MuSe 2025 targets researchers interested in audio-visual emotion recognition, unimodal and multimodal representation learning, health informatics, and NLP-based emotion and sentiment analysis.

Submission Guidelines

In submitting a manuscript to this workshop, the authors acknowledge that no paper substantially similar in content has been submitted to another conference or workshop. Manuscripts should follow the ACM MM2025 paper format. Authors should submit their papers as PDF files. Papers accepted for the workshop will be allocated 6-8 pages (plus additional pages for the references) in the proceedings of ACM MM 2025. MuSe2025 reviewing is double-blind. Reviewing will be by members of the program committee. Each paper will receive at least three reviews. Acceptance will be based on relevance to the workshop, novelty, and technical quality.

List of Topics

• Affect Recognition & Sentiment Analysis
  • Emotion, humor, irony, empathy, and social bonding detection across modalities.
• Social Perception & Non-Verbal Cues
  • Trust, dominance, deception, body language, and interpersonal rapport analysis.
• LLMs & Multimodal Fusion
  • Using LLMs for embedding, fusion, and affect understanding.
• Emotional TTS & Speech Synthesis
  • Expressive, adaptive, and real-time emotion-based speech generation.
• Fairness & Explainability
  • Bias mitigation, transparent AI, and ethical considerations in emotion AI.
• Conversational AI & Human-AI Interaction
  • Empathetic, charismatic virtual agents, and affect-aware systems.
• Continual Learning & Adaptation
  • Lifelong learning, self-supervision, and domain adaptation in sentiment models.

Committees

Program Committee

        tba, see: https://www.muse-challenge.org/people/tpc

Organizing committee

• Shahin Amiriparian: Technical University of Munich, DE. shahin.amiriparian@tum.de
• Björn W. Schuller: Imperial College London, UK. schuller@ieee.org
• Erik Cambria: NTU/SenticNet, SG. cambria@ntu.edu.sg
• Lukas Christ: Technical University of Munich, DE. lukas.christ@tum.de
• Maurice Gerczuk: Technical University of Munich, DE. maurice.gerczuk@tum.de

Publication

MuSe2025 proceedings will be published in ACM Multimedia.

Venue

The conference will be held in the Royal Convention Center in Dublin, Ireland.

Contact

All questions about submissions should be emailed to contact.muse2020@gmail.com

Sponsors

SenticNet, audEERING