MLKD logo   Machine Learning &
Knowledge Discovery Group

Publication Details

  Author(s): E. Spyromitros-Xioufis, E. Stachtiari, G. Tsoumakas, I. Vlahavas.

Title: “A Hybrid Approach for Cold-start Recommendations of Videolectures”.

Availability: Click here to download the PDF (Acrobat Reader) file (12 pages).

Keywords: hybrid recommender, cold-start problem, query expansion.

Appeared in: Proceedings ECML/PKDD 2011 Discovery Challenge Workshop, Athens, Greece, 2011.

Abstract: This paper presents the solution which ranked 2nd in the "cold-start" recommendations task of the ECML/PKDD 2011 discovery challenge. The task was the recommendation of new videolectures to new users of the Videolectures.netWeb site. The proposed solution is a hybrid recommendation approach which combines content-based and collaborative information. Structured and unstructured textual attributes which describe each lecture are synthesized to create a vector representation with tf/idf weights. Collaborative information is incorporated for query expansion with a novel method which identies neighboring lectures in a co-viewing graph and uses them to supplement missing attributes. The cosine similarity measure is used to nd similar lectures and nal recommendations are made by also accounting the coexistence duration of lectures. The results of the competition show that the proposed approach is able to give accurate "cold-start" recommendations.

Relevant Links: Discovery Challenge