AI-Based Facial Expression Detection as a Support Feature for Cybercounseling: A Systematic Literature Review

The rapid expansion of digital mental health services has increased the use of cybercounseling, while simultaneously introducing challenges in interpreting nonverbal cues, particularly facial expressions, within technology-mediated interactions. This study aims to systematically examine the potential of artificial intelligence (AI) in facial expression detection as a support feature in cybercounseling. A systematic literature review (SLR) was conducted following PRISMA guidelines, drawing from multiple indexed academic databases. The included studies covered AI-based facial expression recognition, micro-expression analysis, depression detection, and relevant multimodal approaches. The findings indicate that deep learning–based models are capable of identifying facial patterns associated with emotional and psychological conditions, including depression, with high accuracy in controlled datasets. Micro-expression analysis further enables the detection of subtle and concealed affective signals that are difficult to observe through human perception alone. However, the results also demonstrate that facial expressions cannot be treated as direct representations of psychological states, as their interpretation is influenced by expression intensity, contextual factors, and individual variability. In addition, multimodal approaches integrating facial, vocal, and physiological signals provide more comprehensive and reliable insights compared to unimodal systems. These findings suggest that AI-based facial expression detection holds potential as a supportive tool in cybercounseling, particularly for enhancing affective observation and identifying subtle emotional cues. Nevertheless, its use should remain complementary to professional judgment rather than as a standalone diagnostic mechanism. Current limitations include the dominance of dataset-driven studies, limited application in real counseling contexts, and insufficient attention to ethical considerations.