Japanese Language Review Mining using Translators, Word Embedding and ML Techniques

Most individuals rely on translation to communicate and comprehend other languages. The main driving force behind this study is determining which translator, along with the blend of word embedding and Machine Learning(ML)techniques, has greater accuracy when working with the Japanese Language. Business owners struggle to understand how their products perform in Japan and receive feedback to improve it. Japanese is among the most complex languages to read and write. The issue can be resolved by classifying reviews and ratings into separate groups, such as excellent and negative so business owners can improve their products based on the reviews. This study examines the reviews and ratings from the Japanese-language Amazon Product Review dataset. These reviews have been translated into English using three different translators (Google - GT, Microsoft - MT, and Python - PT). The data for each translator is then subjected to a combination of word embedding techniques (Count Vector, TF-IDF, and Word2vec) and machine learning techniques (Logistic Regression (LR), Support Vector Machine (SVM), Random Forest Classifier (RF), Decision Tree Classifier (DT), and XG Boost Classifier (XGB). According to the study's findings, the Python Translator, combined with a TF-IDF and LR mix, exceeds all other translators with an accuracy of 89.96%.