On the State of NLP Approaches to Modeling Depression in Social Media: A Post-COVID-19 Outlook

2024-10-11

IEEE journal of biomedical and health informatics

AI Summary

The COVID-19 pandemic triggered a >50% global surge in depressive symptoms, substantially altering the data distribution and semantic patterns of social media text—causing severe performance degradation in pre-pandemic NLP-based depression detection models. This work systematically reviews post-pandemic NLP methodologies for depression modeling on social media, uncovering for the first time the paradigm shift in modeling strategies before versus after the pandemic. We propose a dynamic modeling framework tailored to public health crises, integrating deep learning, representation learning, and multimodal fusion to accommodate pandemic-specific corpora and emerging annotated datasets. We further diagnose the root causes of model degradation and enhance robustness, fairness, and interpretability accordingly. Additionally, we identify novel ethical governance challenges—including data bias, privacy leakage, and algorithmic accountability—in crisis contexts. The study provides both methodological foundations and actionable pathways for AI-driven mental health interventions.

Technology Category

• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Computational approaches to predicting mental health conditions in social media have been substantially explored in the past years. Multiple reviews have been published on this topic, providing the community with comprehensive accounts of the research in this area. Among all mental health conditions, depression is the most widely studied due to its worldwide prevalence. The COVID-19 global pandemic, starting in early 2020, has had a great impact on mental health worldwide. Harsh measures employed by governments to slow the spread of the virus (e.g., lockdowns) and the subsequent economic downturn experienced in many countries have significantly impacted people's lives and mental health. Studies have shown a substantial increase of above 50% in the rate of depression in the population. In this context, we present a review on natural language processing (NLP) approaches to modeling depression in social media, providing the reader with a post-COVID-19 outlook. This review contributes to the understanding of the impacts of the pandemic on modeling depression in social media. We outline how state-of-the-art approaches and new datasets have been used in the context of the COVID-19 pandemic. Finally, we also discuss ethical issues in collecting and processing mental health data, considering fairness, accountability, and ethics.

Problem

• Review NLP approaches for modeling depression in social media post-COVID-19.
• Analyze impact of COVID-19 on depression rates and mental health modeling.
• Discuss ethical issues in mental health data collection and processing.

Innovation

• NLP techniques model depression in social media.
• State-of-the-art approaches analyze COVID-19 impacts.
• Ethical considerations in mental health data processing.