Skip to Content
You are currently on the new version of our website. Access the old version .
  • Review
  • Open Access

26 January 2026

17 Pages

Application of Artificial Intelligence in Social Media Depression Detection: A Narrative Review from Temporal Analysis

,
,
,
,
,
,
,
,
…
1
Santo Stefano Rehabilitation Institute, Porto Potenza Picena 62016, MC, Italy
2
Units of Psychiatry, Ast Fermo, 63900 Fermo, FM, Italy
3
School of Pharmacy, Experimental Center and Public Health “Stefania Scuri”, 62032 Camerino, MC, Italy
4
Department of Pharmacy, Health and Nutritional Sciences (DFSSN), University of Calabria, 87036 Rende, CS, Italy

Abstract

Background: Depression remains a major global mental health concern, significantly intensified during the COVID-19 pandemic. As social media usage surged during this period, it emerged as a valuable source for identifying early signs of depression. Artificial intelligence (AI) offers powerful tools to analyze large volumes of user-generated content, enabling timely and effective detection of depressive symptoms. This review aims to preliminarily explore and compare evidence on the use of AI models for detecting depression in social content across the pre-, during, and post-pandemic phases, assessing their effectiveness and limitations. Methods: A narrative literature review was conducted using PubMed and Scopus, following the SANRA guidelines to ensure methodological quality and reproducibility. The study was pre-registered in the OSF database and employed the PICOS framework for the strategy. Inclusion criteria comprised studies in English from the past 10 years that analyzed depression detection via AI, machine learning (ML), and deep learning (DL) applied to textual data, images, and social metadata. This review addresses the following four research questions: (1) whether AI models improved effectiveness in detecting depression during/after the pandemic vs. pre-pandemic; (2) whether textual, visual, or multimodal data approaches became more effective during the pandemic; (3) whether AI models better addressed technical challenges (data quality/diversity) post-pandemic; and (4) whether strategies for responsible AI implementation improved during/after the pandemic. Results: Out of 349 identified records, nine primary studies were included, as most excluded articles had a predominantly technical focus and did not meet the clinical relevance criteria. AI models demonstrated strong potential in detecting depression, particularly through text-based classification and social content analysis. Several studies reported high predictive performance, with notable improvements in accuracy and sensitivity during and after the pandemic, although evidence remains limited. Conclusions: Our preliminary analysis suggests that AI-based depression detection on social media shows potential for clinical use, highlighting interdisciplinary collaboration, ethical considerations, and patient-centered approaches. These findings require confirmation and validation through larger, well-designed systematic reviews.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.