Back to AI News
arxiv

InertiaMPDD: Multimodal Personalized Depression Detection via Emotional Inertia-Inspired Dynamics Modeling

The paper introduces InertiaMPDD, a multimodal depression screening method that models emotional inertia by learning healthy next-state patterns with a world-model-inspired latent predictor. It derives reference-derived emotional dynamics descriptors from deviations, residual decay rates, and Jacobian spectral properties, and evaluates them as candidate proxy biomarkers for standalone screening and personalized decision correction. Across five cohorts from four datasets, fusion reaches 98.41% F1 on D-Vlog and 84.98% on LMVD, while standalone descriptors outperform fixed additive fusion on MPDD but discriminate weakly on AVEC2014. The findings highlight that reference informativeness and fusion benefit are distinct and context-dependent.

AI Brief

This is a concrete recent research contribution with novel emotional-dynamics modeling and clear evaluation across multiple depression detection datasets.

arXiv:2611.16647v1 Announce Type: new Abstract: Multimodal depression screening estimates risk from speech, visual behavior and language. Current methods mainly predict labels, with limited evidence of departures from a non-depressed reference. Recording-level supervision also leaves fine-grained emotional dynamics unannotated. Motivated by emotional inertia, the persistence of affect, InertiaMPDD learns healthy next-state patterns using a world-model-inspired latent predictor. Using pretrained multimodal representations, it predicts from observed history and context. Reference deviation, residual decay rate and a Jacobian spectral descriptor form reference-derived emotional dynamics descriptors, evaluated as candidate proxy biomarkers for standalone screening and personalized decision correction. Across five cohorts from four datasets, fusion reaches 98.41% F1 on D-Vlog and 84.98% on LMVD. Standalone descriptors outperform fixed additive fusion on MPDD but discriminate weakly on AVEC2014. These findings distinguish reference informativeness from fusion benefit and reveal context-dependent utility.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!