<![CDATA[E-commerce apps have become an important part of modern life, with user reviews playing a crucial role in assessing platform performance and identifying areas for improvement. This research aims to apply the Distilled Bidirectional Encoder Representations from Transformers (DistilBERT) model to analyze the sentiment contained in user reviews of Tokopedia and Shopee apps on the Google Play Store. Along with the rapid growth of e-commerce in Indonesia, platforms such as Tokopedia and Shopee have become an important component in facilitating fast and easy online transactions. User reviews on these platforms are a valuable source of information for evaluating customer satisfaction, but the increasing volume of reviews makes manual sentiment analysis inefficient. This research uses a dataset of Indonesian-language reviews on Tokopedia and Shopee Apps on Google Play Store to classify sentiments into positive and negative categories by utilizing DistilBERT, which is a lightweight variant of BERT with the ability to efficiently process large data without sacrificing accuracy. The results of this analysis provide insights that can assist e-commerce platforms in improving user experience as well as support data-driven decision-making for application development. This research contributes to the application of natural language processing (NLP) technology for sentiment analysis in the context of e-commerce in Indonesia.]]>
Copyrights © 2024
