Abstract
This paper focuses on the issue of automating the multi-label classification of users' text posts in online social networks. This classification is based on previously developed criteria to correlate post types with the evaluation of the severity of psychological features of the user. The presented model for classification is based on a neural network with long short-term memory architecture. The results will help to partially automate the process of making recommendations to improve the protection of users from social engineering attacks.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have