Towards Metadata-Aware Algorithms for Recommender Systems

As recommender systems (RS) allow means of guiding consumers through the overloaded choices of products available, the recommendation problem has always been of great interest for both academic and industry. Metadata such as content information about the items (attributes) have typically been used to enrich RS algorithms. Recently, the trend of employing RS has expanded to other e-communities such as social tagging systems, inspiring the possibility to exploit tags to enhance RS. This book reports several research gaps in metadata-aware RS algorithms. In particular, it discusses attribute-aware RS algorithms focusing on the overlooked item prediction problem as well as the new emerging challenge of tag-aware RS algorithms.

The Author: Karen H. L. Tso-Sutter received her Bachelor in Electrical Engineering at the University of British Columbia in 2002, a Master in Communication and Media Engineering at the University of Applied Science Offenburg (FH Offenburg) in 2004. From 2004 to 2006, she pursued her Ph.D. in Computer Science at the University of Freiburg im Breisgau, researching on attribute-aware recommender systems. In 2006, she continued her Ph.D. studies at the Information Systems and Machine Learning Lab (ISMLL) at the University of Hildesheim as the team moved. She is currently working as a researcher at SAP Research in Darmstadt since 2008.