Research on user modeling based on deep expression learning

    Recently, with the growth of Internet, online platforms such as social media and online shopping website are getting more and more popular. People can access to what they like and need on these websites. Understanding user interest and behavior, analyzing user data, and conducting research on user modeling has great practical meaning. Such research can promote the application of personalized recommendation, online advertising, abnormal detection and so on. Currently, deep representation learning has succeeded in areas such as image and video processing, and we provide solutions for several key problems of user modeling in this talk. These solutions are context-aware representations of users and items in context-aware recommender systems, sequential user behavior prediction based on recurrent neural networks, compatibility and recommendation based on visual features, misinformation detection methods based on the attention mechanism and CNN.