CIOSOS: Combined Idiomatic-Ontology Based Sentiment Orientation System for Trust Reputation in E-commerce

Abstract

Due to the abundant amount of Customer's Reviews available in E-commerce platforms, Trust Reputation Systems remain reliable means to determine, circulate and restore the credibility and reputation of reviewers and their provided reviews. In fact before starting the process of Reputation score's calculation, we need to develop an accurate Sentiment orientation System able to extract opinion expressions, analyze them and determine the sentiment orientation of the Review and then classify it into positive, negative and objective. In this paper, we propose a novel semi-supervised approach which is a Combined Idiomatic-Ontology based Sentiment Orientation System (CIOSOS) that realizes a domain-dependent sentiment analysis of reviews. The main contribution of the system is to expand the general opinion lexicon SentiWordNet to a custom-made opinion lexicon (SentiWordNet++) with domain-dependent "opinion indicators" as well as "idiomatic expressions". The system relies also on a semi-supervised learning method that uses the general lexicon WordNet to identify synonyms or antonyms of the expanded terms and get their polarities from SentiWordNet and then store them in SentiWordNet++. The Sentiment polarity and the classification of the review provided by the CIOSOS is used as an input of our Reputation Algorithm proposed in previous papers in order to generate the Reputation score of the reviewer. We also provide an improvement in calculation method used to generate a "granular" reputation score of a feature or subfeature of the product.

Security based partner selection in Inter-organizational workflow systems

“…Trust is a subjective evaluation of the potential outcomes and risks involved by relying on a partner [6].…”

“…Feedbacks, scores, recommendations and any other information given by organizations are very important for the trust reputation assessment. However, the reliability of this information needs to be verified [6]. There are many works that aim to calculate the trustworthiness level in the literature; In [17], authors defined a trust level algorithm attempting to calculate the Certificate Authority (CA) trustworthiness value.…”

“…It depends on three parameters that are the CA reputation score value as well as its CP quality and its security maturity level. In [6], the authors proposed a Sentiment based Trust and Reputation System namedSentiTrustCom (STC), which aimed to compute most reliable reputation scores for reviewers and products in ecommerce applications. As a future work, we will propose an extended algorithm for calculating a trust and reputation level of each organization in PN based on the work presented in [6].…”

Customer Product Review Summarization over time for Competitive Intelligence

“…This kind of summarization is useless in CI because it loses some detailed information, which is important to inform the decision maker of an organization regarding the development and marketing of a product/service. However, summaries based on features provide information about different features and show what customers usually try to search while referring to opinions that rend these types of summaries of great demand in many application domains like: recommender system (Ładyzẏński and Grzegorzewski, 2014 [17]) and trust reputation (Rahimi and Bakkali, 2015 [23]) with different languages such as English (Kansal and Toshniwal, 2014 [15]), Chinese (Zhou et al, 2016 [31]), Arabic (Abd-Elhamid et al, 2016 [1]) and Italian (Maisto and Pelosi, 2014 [21]). However, the large availability of reviews shared in English allows researchers to focus on this language in their works.…”

ArchiRI - uma arquitetura baseada em ontologias para a troca de informações de reputação

“…CIOSOS [12] é um sistema que utiliza uma ontologia idiomática formada por indicadores de opinião que dependem do domínio, bem como expressões idiomáticas para analisar os comentários de clientes disponíveis em plataformas de e-commerce. Esses comentários são analisados com o objetivo de determinar o sentimento associado ao comentário e, em seguida, classificá-los em positivo ou negativo, e o seu objetivo.…”