@inproceedings{du-etal-2025-sentiment,
    title = "Sentiment Analysis on Video Transcripts: Comparing the Value of Textual and Multimodal Annotations",
    author = "Du, Quanqi  and
      De Langhe, Loic  and
      Lefever, Els  and
      Hoste, Veronique",
    editor = "Bak, JinYeong  and
      Goot, Rob van der  and
      Jang, Hyeju  and
      Buaphet, Weerayut  and
      Ramponi, Alan  and
      Xu, Wei  and
      Ritter, Alan",
    booktitle = "Proceedings of the Tenth Workshop on Noisy and User-generated Text",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.wnut-1.2/",
    pages = "10--15",
    ISBN = "979-8-89176-232-9",
    abstract = "This study explores the differences between textual and multimodal sentiment annotations on videos and their impact on transcript-based sentiment modelling. Using the UniC and CH-SIMS datasets which are annotated at both the unimodal and multimodal level, we conducted a statistical analysis and sentiment modelling experiments. Results reveal significant differences between the two annotation types, with textual annotations yielding better performance in sentiment modelling and demonstrating superior generalization ability. These findings highlight the challenges of cross-modality generalization and provide insights for advancing sentiment analysis."
}