Internet technologies including social networks allow users to easily communicate with each other. This provides us an interesting resources space to early detection of abnormal behavior such as mental disorders. Important mental factors were initially proposed in some psychological solutions. Recently, machine learning-based approaches are proposed and tend to exploit the large data that social networks can provide to detect abnormal behavior in its early stage. In this paper, we propose a set of classifiers-based troubles detection in the context of social media. Diverse unit classifiers are used including messages toxicity detection, gender classifier, age estimation, and personality estimation. Outputs of these classifiers can be combined to intercept abnormal behavior of profiles that can represent a risk. Our different classifiers are trained by using different datasets in the context of twitter and instagram platforms.
CITATION STYLE
Ansari, F. S., Benslimane, D., Khelifi, A., & Barhamgi, M. (2022). Classifiers-Based Personality Disorders Detection. In Communications in Computer and Information Science (Vol. 1677 CCIS, pp. 115–125). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-20490-6_10
Mendeley helps you to discover research relevant for your work.