METADATA EXTRACTION OF RFIs USING NATURAL LANGUAGE PROCESSING AND MACHINE LEARNING ALGORITHMS

role in the analysis and management of RFI documents. However, these metadata are manually entered in the RFI management system, which results in loss of time and incorrect entries. This study aims to demonstrate that metadata of RFI documents can be extracted and assigned automatically using natural language processing and machine learning algorithms. To achieve this aim, the performance of Naïve Bayes and K-Nearest Neighbor algorithms are evaluated and compared. The results show that machine learning models perform well in automatically extracting the metadata of RFIs and, the performance of machine learning models for each label varies. The findings of this study can be used to develop an artificial intelligence based RFI management system by integrating natural language processing and machine learning models into the system.