A Review on Comparison of Machine Learning Algorithms for Text Classification

• Published in: 2022 5th International Conference on Contemporary Computing and Informatics (IC3I) pp. 1818 - 1823
• Main Authors: Dhingra, Mallika, Dhabliya, Dharmesh, Dubey, M. K., Gupta, Ankur, Reddy, Dhoma Harshavardhan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14.12.2022
• Subjects: Decision Tree; k-Nearest Neighbour; Machine learning; Machine learning algorithms; Naive Bayes; Support Vector Machine; Support vector machine classification; Text categorization; Text classification; Text mining; Web pages; Writing
• DOI: 10.1109/IC3I56241.2022.10072502

The majority of the data is preserved as text (about 75%), hence It is believed that text mining has a significant commercial potential. Unstructured texts continue to be the most readily available source of knowledge, despite the fact that knowledge may be accessed in many other places. Text classification that assigns documents to predetermined categories. Machine learning approaches can categories texts more accurately. The goal of this work is to introduce text classification, give a description of the text classification technique, a general review of the classifiers, and a comparison of a few of the current classifiers. It is based on performance, time complexity, and other factors. On the basis of speed, accuracy, benefits, and drawbacks of existing classification methods such as Decision Tree, Naive Bayes, Support Vector Machine, and k-Nearest Neighbours are compared.