Social network mental diseases (SNMD) like cyber-addiction, information overload, and Internet compulsion have been seen to rise in frequency in recent times. Clinical actions for various mental diseases are now delayed since the symptoms are typically observed in a passive manner. Here, we contend that actively detecting SNMDs at an early stage is made possible by monitoring online social behavior. Rather, we present a data science system called Social Network Mental Disorder Identification (SNMDI) that accurately detects possible cases of SNMD by utilizing attributes taken from social network data. We use SNMDI for huge datasets, conduct characteristic analysis, and examine the traits of three different SNMD kinds. According to the findings, SNMDD holds promise in detecting possible SNMDs in users of online social networks Most notably, early intervention can cause mental health issues, which can seriously harm a person’s ability to function in social situations. To put it briefly, it is preferable to aggressively seek out possible SNMD users in OSNs as soon as possible. Even yet, prior psychological research has used accepted diagnostic criteria to pinpoint a few key mental components. In the past, they employed sensors to identify mental diseases. Techniques from data mining and machine learning were used for the extracted data. Additionally, a number of studies employed multi-method approaches that included distributing questionnaires and requesting respondents’ permission to access and download data from their OSN account at a later time. The detection of mental health issues is aided by big data in OSN.