Answers are grounded in this paper and cite their sources.
Mobile banking is evident in the improvement of business processes in the banking industry. Even so, the m-banking application cannot be separated from the problems experienced by its users. Therefore, further analysis is required. This research proposes a sentiment analysis technique using K-Nearest Neigbor (KNN) algorithm to identify user opinions and reviews of m-banking applications. Three popular m-banking apps were selected for further analysis namely BRImo, BSI Mobile, and Livin' by Mandiri. The analysis shows that BRImo is the most popular m-banking application, with a positive sentiment percentage of 58.25%, Livin' by Mandiri with 22.50%, and BSI Mobile with the lowest percentage of 12.70%. Modeling results using the KNN algorithm with K = 3, 5 and 7 test values show K = 3 has better capabilities. Based on the application, the best modeling is produced on BRImo with 82.9% accuracy, then Livin' by Mandiri with 70.3% accuracy, and BSI Mobile with 71.35% accuracy. Analysis and visualization were also conducted using word clouds to see keywords that are often discussed in reviews. As a result, m-banking apps have problems with difficult login, complicated registration or verification, and balance deduction despite failed transfer status.
No takes yet. Share an insight, caveat, or question.
Munandar et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: