A Sentiment-Based Trust and Reputation System in E-Commerce by Extending SentiWordNet

Abstract

Trust is a decisive factor in e-services and especially in e-commerce. E-customers usually rely on others’ opinions, reviews, recommendations on products, and services to make the right purchase decision. Nevertheless, deceptive reviewers deliberately disseminate fake and dishonest reviews to falsify the products’ reputation. Consequently, there is a need for Trust and Reputation Assessment to aggregate these text reviews and compute their related reputation scores. For this purpose, Natural Language Processing cannot be omitted from the process of generating reputation scores. In this paper, we propose a Trust and Reputation System named SentiTrustCom STC which is composed of two subsystems: (1) A Combined Idiomatic Ontology-based Sentiment Orientation System that employs NLP techniques and extends SentiWordNet to analyze Text reviews and compute their related Sentiment orientation scores; (2) Trust and Reputation Engine that proposes algorithms to generate reliable Trust and Reputation scores using the generated Sentiment Polarities as inputs. STC aims to analyze the users’ behavioral intention in order to detect any ill-intentioned interventions that could falsify the products’ reputation and hence distort the overall trust among reviewers.