Scholarlink

This project aims to analyze the mental health status of LGBTQ communities on Twitter by employing keyword extraction and Latent Dirichlet Allocation (LDA) topic modeling techniques. The dataset used for this study consists of tweets pertaining to LGBTQ-related topics and mental health. The tweets were preprocessed by cleaning and tokenizing them, followed by applying LDA to extract the most prominent topics. Additionally, K-means clustering was utilized to assign users to specific topic groups. Subsequently, the content of the tweets was analyzed to categorize users into six mental health categories: depression, anxiety, PTSD, schizophrenia, eating disorders, and bipolar disorder. The study contributes to a better understanding of the mental health experiences and concerns of the LGBTQ community on Twitter. By employing advanced natural language processing techniques, it identifies the prevailing topics of discussion and provides insights into the mental health status of users within the LGBTQ community. The findings of this project can potentially assist mental health practitioners, researchers, and organizations in tailoring their support and interventions to address the specific needs of LGBTQ individuals.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analyzing Mental Health of Minority Communities on Twitter Using Keyword Extraction and LDA Topic Modeling

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Subhadeep Barua,
  • Akash Mondal,
  • Moumita Chatterjee,
  • Premananda Jana,
  • Dipak Kumar Kole,
  • Dhrubasish Sarkar,
  • Ritwika Chakraborty

摘要

This project aims to analyze the mental health status of LGBTQ communities on Twitter by employing keyword extraction and Latent Dirichlet Allocation (LDA) topic modeling techniques. The dataset used for this study consists of tweets pertaining to LGBTQ-related topics and mental health. The tweets were preprocessed by cleaning and tokenizing them, followed by applying LDA to extract the most prominent topics. Additionally, K-means clustering was utilized to assign users to specific topic groups. Subsequently, the content of the tweets was analyzed to categorize users into six mental health categories: depression, anxiety, PTSD, schizophrenia, eating disorders, and bipolar disorder. The study contributes to a better understanding of the mental health experiences and concerns of the LGBTQ community on Twitter. By employing advanced natural language processing techniques, it identifies the prevailing topics of discussion and provides insights into the mental health status of users within the LGBTQ community. The findings of this project can potentially assist mental health practitioners, researchers, and organizations in tailoring their support and interventions to address the specific needs of LGBTQ individuals.