Summary: | Sentiment analysis study predominantly revolves around classification tasks by Machine Learning. None of these studies had demonstrated the comparative analysis between different type of ML models accuracy level. On the other hand, the banking industry is rapidly embracing digitalization and security-related matters like trust and privacy remain critical factors in influencing customer's acceptance and usage towards those services. Hence, sentiment analysis serves as a powerful tool for banks to gauge customer satisfactory level towards these security services. However, this process is done previously without optimizing the selection of ML models accuracy level. Furthermore, the results are often invisible and kept in manual book. Hence the ultimate goal of this study is to comparatively measure the accuracy performance of different type of ML sentiment analysis accuracy against the Malaysia online banking security services Twitter data (a.k.a X). Subsequently, the report will be visualized through web application. It is done in six-fold methodology namely data collection, data pre-processing and data wrangling, data analysis, model training and finally model testing and evaluations. The result shows Decision tree has achieved the highest accuracy of 76%. © 2024 The Authors.
|