Searching for Old News: User Interests and Behavior within a National Collection

Modeling user interests helps to improve system support or refine recommendations in Interactive Information Retrieval. The aim of this study is to identify user interests in different parts of an online collection and investigate the related search behavior. To do this, we propose to use the metadata of selected facets and clicked documents as features for clustering sessions identified in user logs. We evaluate the session clusters by measuring their stability over a six-month period. We apply our approach to data from the National Library of the Netherlands, a typical digital library with a richly annotated historical newspaper collection and a faceted search interface. Our results show that users interested in specific parts of the collection use different search techniques. We demonstrate that a metadata-based clustering helps to reveal and understand user interests in terms of the collection, and how search behavior is related to specific parts within the collection.