Semantic Recommendations based on Large Unstructured Datasets

Competence CenterInformation Retrieval and Machine Learning
ContactProf. Dr.-Ing. Sahin AlbayrakTill Plumbaum
Partner: Neofonie GmbH


SERUM establishes the basis for a semantic recommender system that calculates high quality recommendations based on a semantic analysis of user behavior and news articles. The aim of the project is to develop a recommender system that computes different types of recommendations independent of a specific use case or domain. The recommendations are personalized and adapted to the specific needs of a user based on a representation of personal interests and preferences. 

Within the SERUM research project, the goal is to recommend entertainment news. The system analyzes the previous reading behavior and music interests of users in order to create personalized news digests. The recommendation system is connected to a semantic knowledge base, which is modeled and managed as an ontology. The semantic knowledge is linked to information from current news articles. Based on this semantic network, new algorithms were developed that analyze the semantic information and the user behavior to compute high quality music and news article recommendations. 

SERUM is a cooperation project of DAI-Labor and Neofonie GmbH and is funded by the Federal Ministry of Economics and Technology.