Tag-Based User Profiling for Social Media Recommendation

Abstract

Making recommendations for social media presents special challenges. As tagging becomes common prac-tice at many social media sites, this research proposes a new approach to user profiling based on the tags as-sociated with one’s personal collection of contents. To utilize the social interaction implied by tagging, a per-sonal profile can be further extended with the tags spec-ified by one’s social contacts. A tag-to-tag matrix is de-fined to enable collaborative filtering-style recommen-dations without explicit user ratings. Experiments with collections of bookmarks and the associated tags from 42,463 users are presented and compared using the dif-ferent views.