Composite match autocompletion (COMMA): A semantic result-oriented autocompletion technique for e-marketplaces

Article type: Research Article

Authors: Porrini, Riccardo^; | Palmonari, Matteo | Vizzari, Giuseppe

Affiliations: DISCo, University of Milano-Bicocca, Viale Sarca 336/14, 20126, Milan, Italy. E-mail: {matteo.palmonari,giuseppe.vizzari,riccardo.porrini}@disco.unimib.it

Note: [] Corresponding author.

Abstract: Autocompletion systems support users in the formulation of queries in different situations, from development environments to the web. In this paper we describe Composite Match Autocompletion (COMMA), a lightweight approach to the introduction of semantics in the realization of a semi-structured data autocompletion matching algorithm. The approach is formally described, then it is applied and evaluated with specific reference to the e-commerce context. The semantic extension to the matching algorithm exploits available information about product categories and distinguishing features of products to enhance the elaboration of exploratory queries. COMMA supports a seamless management of both targeted/precise queries and exploratory/vague ones, combining different filtering and scoring techniques. The algorithm is evaluated with respect both to effectiveness and efficiency in a real-world scenario: the achieved improvement is significant and it is not associated to a sensible increase of computational costs.

Keywords: Autocompletion systems, eCommerce, semantic matching, efficient matching, semi-structured data, exploratives queries

DOI: 10.3233/WIA-140284

Journal: Web Intelligence and Agent Systems: An International Journal, vol. 12, no. 1, pp. 35-49, 2014