Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification

TL;DR

This paper introduces a new dataset and a novel framework to improve multimodal language models' ability to interpret figurative memes related to mental health, leveraging commonsense knowledge for better classification of anxiety symptoms.

Contribution

The paper presents AxiOM, a new dataset for mental health meme classification, and M3H, a framework that integrates commonsense and domain knowledge to enhance interpretative capabilities of MLMs.

Findings

M3H outperforms 6 baselines with 20 variations in metrics.

Achieved 4.20% and 4.66% improvements on weighted-F1.

Demonstrated the importance of commonsense in figurative language understanding.

Abstract

The expression of mental health symptoms through non-traditional means, such as memes, has gained remarkable attention over the past few years, with users often highlighting their mental health struggles through figurative intricacies within memes. While humans rely on commonsense knowledge to interpret these complex expressions, current Multimodal Language Models (MLMs) struggle to capture these figurative aspects inherent in memes. To address this gap, we introduce a novel dataset, AxiOM, derived from the GAD anxiety questionnaire, which categorizes memes into six fine-grained anxiety symptoms. Next, we propose a commonsense and domain-enriched framework, M3H, to enhance MLMs' ability to interpret figurative language and commonsense knowledge. The overarching goal remains to first understand and then classify the mental health symptoms expressed in memes. We benchmark M3H against 6 competitive baselines (with 20 variations), demonstrating improvements in both quantitative and qualitative metrics, including a detailed human evaluation. We observe a clear improvement of 4.20% and 4.66% on weighted-F1 metric. To assess the generalizability, we perform extensive experiments on a public dataset, RESTORE, for depressive symptom identification, presenting an extensive ablation study that highlights the contribution of each module in both datasets. Our findings reveal limitations in existing models and the advantage of employing commonsense to enhance figurative understanding.