Saved in:
Bibliographic Details
Main Authors: Hou, Ruibo, Teng, Shiyu, Liu, Jiaqing, Chai, Shurong, Li, Yinhao, Lin, Lanfen, Chen, Yen-Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.01892
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917057762689024
author Hou, Ruibo
Teng, Shiyu
Liu, Jiaqing
Chai, Shurong
Li, Yinhao
Lin, Lanfen
Chen, Yen-Wei
author_facet Hou, Ruibo
Teng, Shiyu
Liu, Jiaqing
Chai, Shurong
Li, Yinhao
Lin, Lanfen
Chen, Yen-Wei
contents Multimodal deep learning has shown promise in depression detection by integrating text, audio, and video signals. Recent work leverages sentiment analysis to enhance emotional understanding, yet suffers from high computational cost, domain mismatch, and static knowledge limitations. To address these issues, we propose a novel Retrieval-Augmented Generation (RAG) framework. Given a depression-related text, our method retrieves semantically relevant emotional content from a sentiment dataset and uses a Large Language Model (LLM) to generate an Emotion Prompt as an auxiliary modality. This prompt enriches emotional representation and improves interpretability. Experiments on the AVEC 2019 dataset show our approach achieves state-of-the-art performance with CCC of 0.593 and MAE of 3.95, surpassing previous transfer learning and multi-task learning baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01892
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Retrieval-Augmented Multimodal Depression Detection
Hou, Ruibo
Teng, Shiyu
Liu, Jiaqing
Chai, Shurong
Li, Yinhao
Lin, Lanfen
Chen, Yen-Wei
Machine Learning
Computation and Language
Multimodal deep learning has shown promise in depression detection by integrating text, audio, and video signals. Recent work leverages sentiment analysis to enhance emotional understanding, yet suffers from high computational cost, domain mismatch, and static knowledge limitations. To address these issues, we propose a novel Retrieval-Augmented Generation (RAG) framework. Given a depression-related text, our method retrieves semantically relevant emotional content from a sentiment dataset and uses a Large Language Model (LLM) to generate an Emotion Prompt as an auxiliary modality. This prompt enriches emotional representation and improves interpretability. Experiments on the AVEC 2019 dataset show our approach achieves state-of-the-art performance with CCC of 0.593 and MAE of 3.95, surpassing previous transfer learning and multi-task learning baselines.
title Retrieval-Augmented Multimodal Depression Detection
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2511.01892