UTILIZING TEXT MINING TO EXTRACT KNOWLEDGE AND CLASSIFY INFORMATION IN INDUSTRIAL ENGINEERING

Purpose- In the modern information age, organizations face an overwhelming amount of textual data from various sources. The true potential of this data is realized when transformed into actionable knowledge. This study aims to create a text-based model for information classification and knowledge extraction in industrial engineering. Methodology- The research follows a descriptive-survey approach, employing text-mining techniques to analyze a comprehensive dataset of scientific research articles from the Science Direct database between 2015 and 2020. Data preprocessing was performed using Excel, while analysis was conducted with MATLAB software. The proposed model employs the nearest neighbor and support vector machine algorithms for robust text classification and knowledge extraction. Findings- The study demonstrates the model's effectiveness in systematically extracting valuable knowledge from diverse textual sources. It shows that this approach can facilitate information extraction without compromising data integrity, thereby contributing to knowledge management practices in industrial engineering. Conclusion- The text-based model developed in this study provides a reliable method for extracting knowledge from extensive textual datasets. The approach can be applied to other fields beyond industrial engineering, indicating its broader relevance and utility in the contemporary information age. Keywords: Text mining, knowledge extraction, industrial engineering, data preprocessing, support vector machines. JEL Codes: C55, L23, O32