<![CDATA[Technological developments have developed rapidly and impact changing behavior in daily activities. Now, selling and buying activities are carried out in e-commerce services. The increase in e-commerce users is the main factor in improving the quality of e-commerce services. One of the factors to improve the quality of e-commerce services is customer reviews. Customer reviews are useful for shop owners to find out whether the product offered has positive or negative reviews. The large number of customer reviews is the main factor in the difficulty of shop owners in classifying customer reviews. This study proposes classifying customer reviews using ensemble learning with boosting techniques such as XGBoost, AdaBoost, Gradient Boosting, and LightGBM. The use of an ensemble with a boosting technique aims to improve the algorithm’s performance. In a test scenario apply majority voting to produce the best performance from each algorithm. The result shows that the XGBoost algorithm produces higher accuracy than other techniques are 92.30%. On the analysis of matric evaluation of precision, recall, and F1-Score, XGBoost produces higher true positive values than other techniques such as AdaBoost, Gradient Boosting, and Light GBM]]>
Copyrights © 2024
