Social influence-based contrast language analysis framework for clinical decision support systems

Yang X., Joukova A., Ayanso A., Zihayat M.

Decision Support Systems, vol.159, 2022 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 159
  • Publication Date: 2022
  • Doi Number: 10.1016/j.dss.2022.113813
  • Journal Name: Decision Support Systems
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, International Bibliography of Social Sciences, PASCAL, ABI/INFORM, Aerospace Database, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Communication Abstracts, Computer & Applied Sciences, INSPEC, Metadex, Psycinfo, Civil Engineering Abstracts
  • Keywords: Contrast language analysis, Clinical Decision Support System (CDSS), Depression detection, Social network, Contrast language analysis, Clinical Decision Support System (CDSS), Depression detection, Social network
  • TED University Affiliated: No


© 2022 Elsevier B.V.Depression is a leading mental health problem affecting 300 million people globally. Recent studies show that social networks provide a tremendous potential for mental health professionals as a source of supplemental information about their patients. This study presents a methodological framework for clinical decision support systems (CDSSs) through analysis of social network data to distinguish the language usage of individuals with early signs of depression (i.e., contrast language analysis). By analyzing the contrast language patterns of different user groups, we are able to uncover constructive and actionable insights into the pain points and characteristics of users with signs of depression as decision support mechanisms for clinicians during intervention, (early) diagnosis and treatment plans. First, we discover terms that represent contrasting language by analyzing the percentage difference of terms in two user groups, labeled as”depressed” and”non-depressed” for ease of reference. Second, by building topic models based on social network contents, the topic-level contrast features are discovered. Finally, we consider the structure of the social network to discover the network-level contrast features. To illustrate the effectiveness of the proposed framework, we present a case study on early depression detection using a real-world dataset. The proposed framework has methodological contributions in enhancing the features and functionalities of CDSS for clinicians. It also contributes to evidence-based health research through cost-effective data and analytical insights that can supplement or improve the traditional survey and time-consuming interview methods.