News recommendations using CF-IDF

A.C. Hogenboom, F. Frasincar, U. Kaymak, F.M.G. Jong, de

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

153 Downloads (Pure)


Most of the traditional recommendation algorithms are based on TF-IDF, a term-based weighting method. This paper proposes a new method for recommending news items based on the weighting of the occurrences of references to concepts, which we call Concept Frequency-Inverse Document Frequency (CFIDF). In an experimental setup we apply CF-IDF to a set of newswires in which we detect 1; 167 instances of a set of 65 concepts from a domain ontology. The proposed method yields significantly better results with respect to accuracy, recall, and F1 than the TF-IDF method we use as a basis for comparison.
Original languageEnglish
Title of host publicationProceedings of the 23rd Benelux Conference on Artificial Intelligence (BNAIC 2011), November 3-4, 2011, Gent, Belgium
EditorsP. De Causmaecker, J. Maervoet, T. Messelis, K. Verbeeck, T. Vermeulen
Place of PublicationGent
Publication statusPublished - 2011
Event23rd Benelux Conference on Artificial Intelligence (BNAIC 2011) - Gent, Belgium
Duration: 3 Nov 20114 Nov 2011
Conference number: 23


Conference23rd Benelux Conference on Artificial Intelligence (BNAIC 2011)
Abbreviated titleBNAIC 2011


Dive into the research topics of 'News recommendations using CF-IDF'. Together they form a unique fingerprint.

Cite this