Integration of fuzzy logic and a convolutional neural network in three-way decision-making

With the increase in web usage, opinion mining has become a new trend in analysing opinions. Nevertheless, opinion mining still faces huge challenges, such as uncertainty in opinions which can make opinions difficult to interpret using existing opinion mining models. These models have been developed to automate the opinion mining process of the user; however, extant models which use machine learning algorithms have limitations dealing with uncertainties in opinions such as online customer reviews. Fuzzy models were introduced to solve this problem. However, the fuzzy models have issues in regard to large uncertain boundaries. To address this serious issue, this research introduces a decision framework via which positive, negative and boundary regions are classified using fuzzy concepts. Then, a convolutional neural network (CNN) is used to further classify fuzzy concepts originally allocated to the boundary region. The framework uses formal concepts to represent uncertainties and the CNN classifies the boundary region concepts into either positive or negative opinions. A series of experiments was conducted, the outcomes of which suggest the uncertainties in opinions can be effectively handled using our three-way decision-making framework. Our work contributes to boosting the performance of opinion classification models.

Automated summary

With the increase in web usage, opinion mining has become a new trend in analyzing opinions. However, existing opinion mining models face challenges in interpreting uncertain opinions. This research introduces a decision framework that utilizes fuzzy concepts and a convolutional neural network to effectively handle uncertainties in opinions. Experimental results demonstrate that this three-way decision-making framework improves the performance of opinion classification models.