Tagging and Tag Recommendation

Abstract

Tagging has emerged as one of the best ways of associating metadata with objects (e.g., videos, texts) in Web 2.0 applications. Consisting of freely chosen keywords assigned to objects by users, tags represent a simpler, cheaper, and a more natural way of organizing content than a fixed taxonomy with a controlled vocabulary. Moreover, recent studies have demonstrated that among other textual features such as title, description, and user comments, tags are the most effective to support information retrieval (IR) services such as search, automatic classification, and content recommendation. In this context, tag recommendation services aim at assisting users in the tagging process, allowing users to select some of the recommended tags or to come up with new ones. Besides improving user experience, tag recommendation services potentially improve the quality of the generated tags, benefiting IR services that rely on tags as data sources. Besides the obvious benefit of improving the description of the objects, tag recommendation can be directly applied in IR services such as search and query expansion. In this chapter, we will provide the main concepts related to tagging systems, as well as an overview of tag recommendation techniques, dividing them into two stages of the tag recommendation process: (1) the candidate tag extraction and (2) the candidate tag ranking.