Mapping Computer Science Research: Trends, Influences, and Predictions
This provides incremental insights for researchers and institutions to make data-driven decisions on research directions.
This paper tackles the problem of identifying trending research areas in computer science by analyzing papers, citations, and funding data, finding that reference count is the most relevant factor and that a logistic regression model outperforms decision trees with higher accuracy, precision, recall, and F1 score.
This paper explores the current trending research areas in the field of Computer Science (CS) and investigates the factors contributing to their emergence. Leveraging a comprehensive dataset comprising papers, citations, and funding information, we employ advanced machine learning techniques, including Decision Tree and Logistic Regression models, to predict trending research areas. Our analysis reveals that the number of references cited in research papers (Reference Count) plays a pivotal role in determining trending research areas making reference counts the most relevant factor that drives trend in the CS field. Additionally, the influence of NSF grants and patents on trending topics has increased over time. The Logistic Regression model outperforms the Decision Tree model in predicting trends, exhibiting higher accuracy, precision, recall, and F1 score. By surpassing a random guess baseline, our data-driven approach demonstrates higher accuracy and efficacy in identifying trending research areas. The results offer valuable insights into the trending research areas, providing researchers and institutions with a data-driven foundation for decision-making and future research direction.