A hybrid statistical and semantic model for identification of mental health and behavioral disorders using social network analysis

The advent of social networking and open health web forums such as PatientsLikeMe, WebMD, ehealth forum etc. have provided avenues for social user data that can prove instrumental in suggesting futuristic trends in healthcare. Homophily in social networks is a vital contributor for analyzing patterns for medical conditions, diagnosis and treatment options. Since, members with similar medical issues contribute to a common discussion pool; this offers a rich source of information that can be utilized. This paper intends to explore growing trends in Mental Health and Behavioral Studies (MHB) which lays emphasis on co-existing conditions resulting in comorbidity. We present a novel approach where personality traits inferred from unstructured text of patients and general social users are compared via statistical analysis. This is achieved by our Psychiatric Disorder Determination (PDD) algorithm. Further, Social media data of users showing personality traits of patients is subjected to semantic based text classification using Natural Language Processing (NLP) and Ontology Based Information Extraction (OBIE) in our Addiction Category Determination (ACD) algorithm. This provides categorization of user journals to common topics of discussion by referring to ontologies DBpedia, Freebase and YAGO2s. The final category hence obtained can be predicted to be a trending subject of concern for users with Psychiatric disorders developing Addictive behavioral personalities.