Assessing the effectiveness of a three-way decision-making framework with multiple features in simulating human judgement of opinion classification

Abstract

Three-way opinion classification (3WOC) models are based on a human perspective of opinion classification and offer human-like decision-making capabilities. The purpose of this study was to determine the effectiveness of a three-way decision-making framework with multiple features (fuzzy features and semantic features) in simulating human judgement of opinions. This was an quantitative study. A simple prototype of the three-way decision model was run against the Amazon Musical Instrument dataset to evaluate the model. The data used to verify the results were collected from 125 respondents via an online survey. The participants tested the model in context, then immediately filled in the online questionnaire. Results show that the statistical correlation between semantic features and fuzzy feature is low. Therefore, classification coverage and accuracy can be increased when both types of features are used together rather than using one type of feature alone. With the integration of semantic features and fuzzy features, we found that our three-way decision model performs better than a two-way classification model. Furthermore, the 3WOC model is a simulation of human judgements executed when people make decisions. Finally, we offer usability recommendations based on our analysis. A three-way decision-making framework is a better solution to simulate human judgement of opinion classification than a two-way decision model. The research outcomes will help in the development of better opinion classification systems that can support businesses and organisations to make strategic plans to improve their products or services based on customer preference patterns.