Integration of Fuzzy and LSTM in Three-Way Decisions

Abstract

Recently, a three-way decision concept is studied to handle the uncertainty and incompleteness in the given attribute set based on acceptance, rejection, and uncertain regions. A three-way decision is a vital method in solving the problem of uncertainty in opinion mining models.There are models developed to solve the problem of uncertainty under three-way decision theory. However, with the classification performance of existing models, we further investigate the formulation of three-way regions using fuzzy concepts and Long Short Term Memory (LSTM). To demonstrate the effectiveness of the method, experiments were conducted using a movie review and an ebook review datasets. The experimental results show that the proposed three-way framework is effective for dealing with uncertainties in opinions.