Using text mining to identify and prioritize user needs for digital mental health services on Chinese online...

Area of Science:

• Digital Mental Health
• Text Mining
• User Needs Analysis

Background:

• Digital mental health platforms are increasingly utilized for support.
• Understanding specific user needs is crucial for service optimization.
• Text mining offers a method to analyze large volumes of user feedback.

Purpose of the Study:

• To identify user needs on digital mental health platforms.
• To guide service optimization through text mining insights.
• To quantify user needs using a novel need-intensity formula.

Main Methods:

• Collected 25,131 user comments via web scraping.
• Applied Latent Dirichlet Allocation (LDA) for topic modeling.
• Conducted sentiment and semantic network analyses; integrated LDA with a need-intensity formula for quantitative prioritization.

Main Results:

• Identified six main topics, with 'Career and Personal Growth' (20.40%) and 'Social and Emotional Support' (20.15%) being most prevalent.
• Sentiment analysis revealed over 77% of comments expressed negative emotions.
• Need-intensity analysis prioritized 'Career and Personal Growth' (0.94) and 'Social and Emotional Support' (0.88) as the most pressing user needs.

Conclusions:

• Users express significant needs in emotion management, psychological counseling, and familial/social support.
• Recommended targeted features: career stress triage pathways and secure family linkage options.
• Actionable strategies can enhance service precision, user engagement, and optimize digital mental health delivery.