WhaleOptNB: A Method for Automated Biomedical Text Document Classification

In recent years, there has been a meteoric rise in the amount of digital information stored in the biomedical industry due to the rapid growth of the internet and other information technologies. Automated biomedical text classification has become an effective and robust method of accessing the increased amount of technical and medical literature in the biomedical sector through the classification of multiple source documents while preserving the significantly informative data to manage the enormous amount of biomedical data currently available. This is accomplished by automating the classification of multiple source documents in the biomedical field. Therefore, multi-document biomedical text classification plays an essential role in resolving the problem of gaining access to accurate and up-to-date information. A Whale Optimization Algorithm-based Weighted Naive Bayes Classifier (WhaleOptNB) for text document classification is proposed. A biomedical text document dataset is collected and preprocessed. Then, the preprocessed data's features are extracted using the Term Frequency-Inverse Document Frequency (TF-IDF). To classify the biomedical text document, WhaleOptNB is utilized. To prove the efficiency of the proposed methodology, it is compared with existing methods. Simulation results show that the proposed method outperforms conventional methods.