Publications and Messages Exchanged in a Chat Room Analysis
摘要
In this article, we will present the use of machine learning techniques to create a profiling system. This system aims to know and allow users to define their needs and preferences, by providing them with appropriate content. Our work presents a profiling system based on publications posted in a professional network. Our system is composed of two parts. The first part is dedicated to the preparation and extraction of information based on topic modeling, sentiment analysis, and emotion analysis, and the second part is to the profiling of the platform’s collaborators (centers of interests, psychological profile, relational profile).