Aspect-Based Sentiment Analysis Using Mini-Window Locating Attention for Vietnamese E-commerce Reviews

Abstract

This article illustrates a system developed to tackle Aspect-based sentiment classification for Vietnamese E-commerce reviews. We employ supervised learning models based on Deep Learning application and multiple classic classifiers such as Random Forest, Decision Tree, Support Vector Machine, etc. to sort out the model performs best with our dataset. Our method obtained the maximum Micro-Average and Macro-Average Performance of 95%. Furthermore, we present how our Vietnamese manually-annotated multi-aspect dataset in two domains: Technology and Mother & Baby was prepared.