Semantic Pattern-based Recommender

V. Maccatrozzo, D. Ceolin, L.M. Aroyo, P.T. Groth

Research output: Chapter in Book / Report / Conference proceedingChapterAcademicpeer-review


This paper presents a novel approach for Linked Data-based
recommender systems by means of semantic patterns. We associate to
each pattern the rating of the arrival book (0 or 1) and compute user
profiles by aggregating, for each book in the user training set, the ratings
of all the patterns pointing to that book. Ratings are aggregated by
estimating the expected value of a Beta distribution describing the rating
given to the book. Our approach allows the determination of a rating for
a book, even if the book is poorly connected with user profile. It allows
for a “prudent” estimation thanks to smoothing, obtained by using the
Beta distribution. If many patterns are available, it considers all the
contributions. Nevertheless, it allows for a lightweight computation of
ratings as it exploits the knowledge encoded in the patterns. Without
any setup of the system, this approach allowed us to reach a precision of
0.60 and an overall F-measure of about 0.52.
Original languageEnglish
Title of host publicationSemWebEval 2014
EditorsV. Presutti, M. Stankovic, E. Cambria, I. Cantador, A. Di Iorio, T. Di Noia, C. Lange, D. Reforgiato Recupero, A. Tordai
Place of PublicationHeidelberg
Number of pages5
Publication statusPublished - 2014

Publication series


Bibliographical note


Dive into the research topics of 'Semantic Pattern-based Recommender'. Together they form a unique fingerprint.

Cite this