Date of Publication :8th December 2023

Abstract: This paper attempts to modify the Content-Based Filtering Algorithm (which is one of the known algorithms in Recommender Systems) using the Levenshtein Distance for Art Recommendation System. Recommender Systems are vital in today’s age since there is so much information available on the Internet, and these systems are the ones in charge of filtering these massive amounts of data to fit your interests. This paper focuses on one drawback of the algorithm which is “Overspecialization”, that is when the algorithm recommends items to the user that are very much similar to the user’s previous activities. The Researchers gathered the data from data.world which consists of different information about each artwork and its artist. The findings imply that the use of the modified algorithm has improved in comparison to the original. Just like the original Content-Based Filtering, it suggests to users artworks that are based on their previous interests, but it also recommends fresh and familiar types of artworks that may expand the user’s interests.

Reference :