Assessing The Efficacy Of Machine Learning Approaches In Classifying AI Research Papers

(AI) research has resulted in a vast volume of academic publications, creating a pressing need for efficient methods to organize and classify these documents. This paper investigates the application of text mining techniques combined with machine learning algorithms to automate the classification of AI research papers. We specifically compare the performance of Random Forest and Support Vector Machines (SVM) to determine their effectiveness in categorizing a diverse dataset of AI literature. Our approach emphasizes the role of feature extraction and selection, particularly using term frequency-inverse document frequency (TF-IDF), to enhance the classification accuracy. Experimental results reveal that Random Forest outperforms SVM, achieving the highest accuracy due to its ability to handle high-dimensional data and complex decision boundaries. The superior performance of Random Forest underscores its suitability for classifying AI research papers, offering a robust solution for managing the ever-growing corpus of AI literature. These findings provide valuable insights into the development of automated classification systems, which are crucial for improving information retrieval and facilitating a deeper understanding of AI research trends.