This paper presents our approach to the first Multimodal Personality-Aware Depression Detection Challenge, focusing on multimodal depression detection using machine learning and deep learning models. We explore and compare the performance of XGBoost, transformer-based architectures, and large language models (LLMs) on audio, video, and text features. Our results highlight the strengths and limitations of each type of model in capturing depression-related signals across modalities, offering insights into effective multimodal representation strategies for mental health prediction.
@article{arxiv.2508.20805,
title = {Exploring Machine Learning and Language Models for Multimodal Depression Detection},
author = {Javier Si Zhao Hong and Timothy Zoe Delaya and Sherwyn Chan Yin Kit and Pai Chet Ng and Xiaoxiao Miao},
journal= {arXiv preprint arXiv:2508.20805},
year = {2025}
}