A Recommender System Based on the Analysis of Personality Traits in Telegram Social Network
Subject Areas : هوش مصنوعی و رباتیکMohammad Javad shayegan 1 , mohadeseh valizadeh 2
1 - University of Science and Culture
2 - Department of Computer Engineering, University of Science and Culture, Tehran,Iran
Keywords: Users' Behavior, Recommender Systems, Social Networks, Telegram, Personality Analysis,
Abstract :
Analysis of personality traits of individuals has always been one of the interesting research topics. In addition, achieving personality traits based on data obtained from individuals' behavior is a challenging issue. Most people spend most of their time on social media and may engage in behaviors that represent a character in cyberspace. There are many social networks today, one of which is the Telegram social network. Telegram also has a large audience in Iran and people use it to communicate, interact with others, educate, introduce products and so on. This research seeks to find out how a recommendation system can be built based on the personality traits of individuals. For this purpose, the personality of the users of a telegram group is identified using three algorithms, Cosine Similarity, MLP and Bayes, and finally, with the help of a recommending system, telegram channels tailored to each individual's personality are suggested to him. The research results show that this recommending system has attracted 65.42% of users' satisfaction.