<![CDATA[User reviews of mobile applications have become a valuable source of information for evaluating the quality of an application. It is crucial for application developers to understand what users express in their reviews. One aspect that can be analyzed from user reviews is Non-Functional Requirement (NFR). Classifying reviews based on NFR is essential in understanding how an application can be enhanced. Although user reviews have the potential to provide valuable insights into NFR, manually processing thousands of user reviews is a laborious and inefficient task. Therefore, artificial intelligence methods are employed to automatically classify user reviews into relevant NFR categories. This research discusses the performance comparison of the SVM and IndoBERT algorithms in NFR classification. The study involves collecting application review data from 2018 to 2023, sourced from Google Playstore and Apple Appstore, followed by annotating the review data based on ISO 25010. Subsequently, the data is allocated into training and testing sets with an 80:20 ratio. Further, a data preprocessing phase is conducted, which includes steps such as lowercasing, tokenization, special character removal, text normalization, and text stemming. The next step involves training the SVM and IndoBERT algorithms on the dataset. Finally, the evaluation is carried out by calculating the F1-score. The research results indicate that the IndoBERT model outperforms the SVM model. The IndoBERT algorithm excels in recognizing NFR in reviews, achieving an F1-score of 93%, while the SVM algorithm achieves an F1-score of 91%.]]>
Copyrights © 2024
