While most techniques for recommending digital content have focused on content's similarity, this system makes recommendations to users on the basis of their preferences. The author's personalization system adopts a methodology applicable for Internet service providers as well as news sites. A user preference score prioritizes recommended articles according to their relevance to the user's preferences. A prototype system, applied to an English news site on the Internet, tests the methodology's feasibility and effectiveness.
Index Terms:
digital content, personalization, recommender system, data mining
Citation:
Sung Ho Ha, "Digital Content Recommender on the Internet," IEEE Intelligent Systems, vol. 21, no. 2, pp. 70-77, Mar./Apr. 2006, doi:10.1109/MIS.2006.24