Authors:
Lucia Noce
;
Ignazio Gallo
and
Alessandro Zamberletti
Affiliation:
University of Insubria, Italy
Keyword(s):
Query Suggestion, Product Suggestion, Price Comparison Engines.
Related
Ontology
Subjects/Areas/Topics:
Enterprise Information Systems
;
Personalized Web Sites and Services
;
Recommendation Systems
;
Searching and Browsing
;
Software Agents and Internet Computing
;
Web Information Systems and Technologies
;
Web Interfaces and Applications
Abstract:
Query suggestion is a technique for generating alternative queries to facilitate information seeking, and has become a needful feature that commercial search engines provide to web users. In this paper, we focus on query suggestion for price comparison search engines. In this specific domain, suggestions provided to web users need to be properly generated taking into account whether both the searched and the suggested products are still available for sale. To this end, we propose a novel approach based on a slightly variant of classical query-URL graphs: the query-product click through bipartite graph. Such graph is built using information extracted both from search engine logs and specific domain features such as categories and products popularities. Information collected from the query-product graph can be used to suggest not only related queries but also related products. The proposed model was tested on several challenging datasets, and also compared with a recent competing quer
y suggestion approach specifically designed for price comparison engines. Our solution outperforms the competing approach, achieving higher results both in terms of relevance of the provided suggestions and coverage rates on top-8 suggestions.
(More)