Abstract
Purpose - Previous work highlights two key challenges in searching for information about individual entities (such as persons, places and organisations) over semantic data: query ambiguity and redundant attributes. The purpose of this paper is to consider these challenges and proposes the Attribute ImportanceModel (AIM) for clustering and ranking aggregated entity search to improve the overall users' experience of finding and navigating entities over the Web of Data.
Design/methodology/approach - The proposed model describes three distinct techniques for augmenting semantic search: first, presenting entity type-based query suggestions; second, clustering aggregated attributes; and third, ranking attributes based on their importance to a given query. To evaluate the model, 36 subjects were recruited to experience entity search with and without AIM.
Findings - The experimental results show that the model achieves significant improvements over the default method of semantic aggregated search provided by Sig.ma, a leading entity search and navigation tool.
Originality/value - This proposal develops more informative views for aggregated entity search and exploration to enhance users' understanding of semantic data. The user study is the first to evaluate user interaction with Sig.ma's search capabilities in a systematic way.