Data Mining's Impact on Company Performance Using Consumer Reviews on Social Media: A Case Study of Telecommunication Industry

The industry is currently faced with rapid technological developments, including the challenges of industry 5.0. Therefore, it is necessary to develop advanced technology to improve automation and digitalization in the industrial sector. One of them is mining information from social media data, which produces large amounts of data storage (big data). Thus, there is potential to use social media data as a basis for policies to improve company performance. This study takes a case study of the telecommunications industry in Indonesia, using the Principal Component Analysis (PCA) and Principal Component Regression (PCR) methods. Big data is obtained from social media review data with a period of 33 weeks from unstructured data on telecommunications service products in Indonesia. The text mining stage produces 30 selected words for further analysis with PCA to produce the main components. Based on the evaluation results, the main components formed show a good correlation with the company's performance in the stock market based on five stock index indicators (price-open, high, low, close, and volume); at least there is one main component equation that shows a strong correlation. This shows the potential for using a data mining approach based on social media reviews as a basis for decision-making to improve company performance. Furthermore, the dominant variables formed from PCA are considered to obtain a simple mathematical model.