The study of users’ behaviour prediction has become more and more important in news recommendation area. But in real news networks, the context of user actions is constantly changing and co-evolving, and consequently, traditional methods such as matrix factorization and collaborative filtering can be ineffective due to the volatility of individual’s behaviors and sparsity of individual’s interaction with news articles.
In this project, the students will investigate how the evolution of user communities can be applied to predict user behavior, and how communities are influenced according to time as well as users’ browsing content. Another challenge for students is to apply related technologies to Norwegian language processing.
To carry out this project, the students will integrate social links, semantic contents and temporal information into community discovery and user modelling. Natural language processing, statistical analysis as well as parallel or distributed processing techniques will be adopted. This is an interesting and promising task in the area of customer intelligence and content analysis, which is suitable for one or two students.
This project is a part of the SmartMedia programme at IDI. SmartMedia collaborates with the Norwegian media industry and is investigating the use of semantics and linked data in large-scale real-time news recommendation.
Supervisors: Peng Liu and Lemei Zhang