Evaluation of Personalized Concept-Based Search and Ranked Lists over Linked Open Data.
Melike Şah, Vincent Wade · 2014
Abstract. Linked Open Data (LOD) provides a rich structured data. As the size of LOD grows, accessing the right information becomes more challenging. Es-pecially, the commonly used ranked lists presentation of current LOD search engines is not effective for search tasks in unfamiliar domains. Recently, com-bination of clustering and personalized search gained more attention for this purpose. In this paper, we evaluate the impact of personalized concept-based search in terms of task assistance and user satisfaction, while comparing with the ranked lists. A user study was conducted with 32 subjects. Results showed that the personalized concept-based search enabled users to be more effective and efficient at performing both information gathering and fact finding tasks.