Unravelling Emotional Nuances: A Cross-Linguistic Analysis of Sentiment Differences in Multilingual Movie Versions

Wynn, Adam; Wang, Jingyun; Li, Xiaoyan

Abstract

To facilitate automatic knowledge creation for the learners of intercultural communication, we propose a pipeline that combines AI analytics with human-in-the-loop evaluation. A case study was conducted on the English and Japanese versions of the film ‘Spirited Away’. Speech segments from both versions were extracted and processed using Valence-Arousal-Dominance (VAD) scores and discrete emotion classification, generated by pre-trained Wav2Vec 2.0 models. The segments with the highest discrepancies
in emotions were identified for further analysis by a group of human raters. This approach not only improves the understanding of emotional differences in dubbed media but also benefits researchers studying cross-cultural communications by assisting knowledge discovery and the creation of knowledge pools. These insights may also contribute to the design of intelligent tutoring systems (ITS) for cross-cultural communication education, enhancing the overall learning experience for learners.

Citation

Wynn, A., Wang, J., & Li, X. (2025, June). Unravelling Emotional Nuances: A Cross-Linguistic Analysis of Sentiment Differences in Multilingual Movie Versions. Presented at ITS2025: 21th International Conference on Intelligent Tutoring Systems, Alexandroupolis, Greece

• Presentation Conference Type: Conference Paper (published)
• Conference Name: ITS2025: 21th International Conference on Intelligent Tutoring Systems
• Start Date: Jun 2, 2025
• End Date: Jun 6, 2025
• Acceptance Date: Apr 7, 2025
• Deposit Date: Jul 4, 2025
• Peer Reviewed: Peer Reviewed
• Book Title: Generative Intelligence and Tutoring Systems
• DOI: https://doi.org/10.1007/978-3-031-98281-1_8
• Public URL: https://durham-repository.worktribe.com/output/3783021