EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Depression Detection Using Pretrained Multi-modal Sentiment Analysis Models with Deep Prefix Tuning

Shiyu Teng, Jiaqing Liu, Shurong Chai, Hao Sun, Tomoko Tateyama, Lanfen Lin, Yen-Wei Chen

ACM Transactions on Computing for Healthcare · 30.07.2026 · 7 (3) · 1-26

DOI: 10.1145/3788672 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Computing for Healthcare, online erschienen am 22.06.2026. Verfasst von Shiyu Teng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science KAKENHI, Japanese Ministry of Education, Culture, Sports, Science and Technology, JST CREST.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Depression, a pervasive mental health condition, affects millions globally, challenging early and accurate diagnosis due to its subtle and varied manifestations. Recognizing the critical link between emotional dysregulation and depressive symptoms, our research introduces a pioneering training paradigm that integrates sentiment analysis with depression detection. This approach is motivated by the potential of sentiment data to enrich models with a deeper understanding of emotional states, crucial for identifying depressive patterns. To leverage the nuanced sentiment information without compromising the pretrained model’s integrity, we employ deep prefix tuning. This novel technique allows for targeted model refinement, ensuring that the valuable pretrained structures are not overshadowed by the sparse and specific nature of depression-related data. The empirical results demonstrate superior performance across standard benchmarks, setting a new precedent for multimodal depression detection.

Förderung

  • Japan Society for the Promotion of Science KAKENHI
  • Japanese Ministry of Education, Culture, Sports, Science and Technology
  • JST CREST
  • JST BOOST
  • Natural Science Foundation of Zhejiang Province

Zitieren

APA

Teng, S., Liu, J., Chai, S., Sun, H., Tateyama, T., Lin, L., & Chen, Y. (2026). Enhancing Depression Detection Using Pretrained Multi-modal Sentiment Analysis Models with Deep Prefix Tuning. ACM Transactions on Computing for Healthcare, 7(3), 1-26. https://doi.org/10.1145/3788672

Vancouver

Teng S, Liu J, Chai S, Sun H, Tateyama T, Lin L, et al. Enhancing Depression Detection Using Pretrained Multi-modal Sentiment Analysis Models with Deep Prefix Tuning. ACM Transactions on Computing for Healthcare. 2026;7(3):1-26. doi:10.1145/3788672

BibTeX
@article{Teng2026,
  author = {Teng, Shiyu and Liu, Jiaqing and Chai, Shurong and Sun, Hao and Tateyama, Tomoko and Lin, Lanfen and Chen, Yen-Wei},
  title = {Enhancing Depression Detection Using Pretrained Multi-modal Sentiment Analysis Models with Deep Prefix Tuning},
  journal = {ACM Transactions on Computing for Healthcare},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {1--26},
  doi = {10.1145/3788672}
}
Kostenlos starten →