Applying Text Mining to Understand Customer Perception of Mobile Banking App

In this big data age, it is imperative to replace the traditional data analysis techniques with big data analytics that can deal with both structured and unstructured datasets from various sources. This study's goal is to provide a method for analyzing unstructured data such as online customer reviews of mobile bank app to better understand customer perceptions. For analyzing customer online reviews, this study makes use of a text mining technique. Pre-processing of the extracted review data, analysis of the sentiment of each review, and an understanding of customer perception and evaluation are all part of the research process. This has come up with some important findings—when looking at it from the perspective of the customer, it was possible to determine which aspects of the app-based banking service are most important to them. As a result, service interruptions can be detected and avoided earlier, resulting in higher customer satisfaction levels. IBBL's bank management should focus more on expanding mobile banking's network reach from a practical standpoint. In order to prevent service failures, they can set up a systematic complaint management system that will allow them to identify and address customer complaints early. In this paper, we use sentiment analysis, one of the text mining applications, to measure service quality using customer reviews of a mobile bank.