Master thesis student
Thesis topic: Opening Black-Box Interest Models for Transparent Recommendation
Related project: RIMA
Thesis duration: 02/2020 - 08/2020
Recommendation systems are essential components of our daily life. Today, intelligent recommendation systems are used in many Web-based systems. As recommender systems impact people’s lives in increasingly profound ways, there is a growing need to ensure that the users understand and trust these systems. This has led to the increasing interest in explainable recommender systems.
We aim through this thesis to develop a Web application which uses extracted keywords from research papers to build a user interest profile/model and recommend tweets, Twitter users, papers, and researchers. Further, the application will provide a set of features to explain to the user why certain items are recommended, by opening the black-box user model.