Cross-domain Ontology Construction and Alignment from Online Product Reviews

Abstract

Online customer product reviews often contain detailed sentiment attitudes towards different aspects of products and these online opinions help potential consumers to be familiar with products. The introduction of well-constructed domain ontology from online product reviews helps potential consumers to obtain relevant information about products quickly. Nonetheless, they may compare products in multiple domains for purchase decisions. On this basis, the comparison of products in different domains induces that ontology alignment becomes a fundamental task to form a cross-domain ontology. In this paper, a series of natural language processing approaches are applied to construct two domain ontologies from online product reviews automatically. Next, a new ontology alignment method is proposed for consumers to make purchase decisions regarding cross-domain product comparisons, in which a semantic-based algorithm and a structure-based algorithm are integrated to form a cross-domain ontology. Categories of experiments were conducted on reviews of smartphone and digital camera. Compared with benchmarked alignment tools, the proposed method performed 5% better in terms of F1 on ontology alignment. Finally, a case study with a customer friendly website is illustrated to present how the alignment of cross-domain ontology help consumers on purchase decision support.