MAMAMemeia: Meme-Based Depression Detection

Published:Dec 31, 2025 18:06
1 min read
ArXiv

Analysis

This paper addresses the important and timely problem of identifying depressive symptoms in memes, leveraging LLMs and a multi-agent framework inspired by Cognitive Analytic Therapy. The use of a new resource (RESTOREx) and the significant performance improvement (7.55% in macro-F1) over existing methods are notable contributions. The application of clinical psychology principles to AI is also a key aspect.

Reference

MAMAMemeia improves upon the current state-of-the-art by 7.55% in macro-F1 and is established as the new benchmark compared to over 30 methods.