An In-Depth Analysis of Tags and Controlled Metadata for Book Search

Abstract

Book search for information needs that go beyond standard bibliographic data is far from a solved problem. Such complex information needs often cover a combination of different aspects, such as specific genres or plot elements, engagement or novelty. By design, subject information in controlled vocabularies is not always adequate in covering such complex needs, and social tags have been proposed as an alternative. In this paper we present a large-scale empirical comparison and in-depth analysis of the value of controlled vocabularies and tags for book retrieval using a test collection of over 2 million book records and over 330 real-world book information needs. We find that while tags and controlled vocabulary terms provide complementary performance, tags perform better overall. However, this is not due to a popularity effect; instead, tags are better at matching the language of regular users. Finally, we perform a detailed failure analysis and show, using tags and controlled vocabulary terms, that some request types are inherently more difficult to solve than others.