← Back to Publications List

Scientific Paper’s Domain Prediction Using Classical Machine Learning Models

Students & Supervisors

Student Authors
Md. Rawha Siddiqi Riad
Bachelor of Science in Computer Science & Engineering, FST
Sharier Mahmud Akash
Bachelor of Science in Computer Science & Engineering, FST
Tahmid Hasan
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Dr. Abdus Salam
Associate Professor, Faculty, FST

Abstract

The growth of research publications in different scientific domains is increasing rapidly. So, there is a need to an automated organization or classification system to help in correctly identifying the domain of a research paper. This paper performs a comparative method of classical machine learning algorithms in predicting the research area of scientific papers based on textual data information derived from the title and abstract of the papers. Exactly 40,000 research papers were obtained from arXiv in four domains: Artificial Intelligence, Machine Learning, Computer Vision, and Robotics. Various popular algorithms like Support Vector Machines (SVM), Decision Tree (DT), Random Forest Classification (RF), Naive Bayes Classifier, k-Nearest Neighbors Classifier (KNN), Logistic Regression Classifier, and XGBoost Classifier were used with TF–IDF and Bag of Words with a stratified five-fold cross validation process. Results demonstrate that the overall best algorithms that can be used for classification of research papers belong to the category of XGBoost with a maximum F1 Score of 97.2%, and in terms of result interpretation and discussion, the method focuses on common points of failure of research domains in classifying domains of research papers.

Keywords

research domain classification machine learning TF–IDF BoW text classification NLP domain prediction.

Publication Details

  • Type of Publication:
  • Conference Name: 2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking
  • Date of Conference: 16/04/2026 - 16/04/2026
  • Venue: IT Business Incubator, Chittagong University of Engineering and Technology (CUET), Chattogram, Bangladesh
  • Organizer: IEEE Photonics Society Bangladesh Chapter
View on Publisher