A Scraper Package Based Approach For Mobile Apps Review Mining And Analysis

This paper presents a novel method for mining mobile app evaluations that employs the "scrapper" package and powerful ML algorithms. The idea was to improve app marketing and development by extracting meaningful data from a large database of user reviews. Using a detailed sentiment analysis, the recovered reviews were classified as positive, negative, or neutral. The findings of this study paved the way for subsequent research on user preferences and perceptions. Following that, we applied a number of machine learning techniques to improve the sentiment analysis and categorization accuracy. The accuracy, recall, precision, F1-score, and confusion matrices were used to evaluate the performance of logistic regression, support vector machines (SVMs), neural networks, and Naive Bayes. The results demonstrated that the proposed strategy worked, surpassing baseline sentiment categorization methods by a significant margin. The ROC curve study provided more evidence that the model could distinguish between positive and negative feelings. Finally, by proposing a robust and successful methodology, this study contributes significantly to the field of mobile app review mining. These insights will aid researchers, app marketers, and developers alike by providing a better knowledge of user input and how to maximize app performance.