Performance evaluation of Machine learning algorithms in Biomedical Document Classification

  • Bichitrananda Behera, G.Kumaravelan


Document classification is a prevalent task in Natural Language Processing (NLP) with a broad range of applications in the biomedical domain. In biomedical engineering categorization of biomedical literature into predefined categories becomes a cumbersome task. Hence, building an automatic document classifier using Machine Learning (ML) algorithms for the biomedical databases emerges as a significant task among the scientific community. In addition, empirical evaluation of these state-of-the-art classifiers for biomedical document categorization also becomes a thrust area of research. Hence, this paper examines the deployment of the various forefront ML algorithms in automatic classification of benchmark biomedical datasets like Bio Creative Corpus III, Farm-Ads, and TREC 2006 genetics Track. Finally, the performance measures of the ML classifiers have been evaluated through standard classification metrics like accuracy, precision, recall, and f1-measure.

Keywords: Machine learning, Deep learning, Text Mining, document classification.

How to Cite
Bichitrananda Behera, G.Kumaravelan. (2020). Performance evaluation of Machine learning algorithms in Biomedical Document Classification. International Journal of Advanced Science and Technology, 29(05), 5704 - 5716. Retrieved from