Text classification based on machine learning
Document Type
Conference Proceeding
Publication Date
1-1-2022
Abstract
Under the era of technical surge in recent years, the weight of artificial intelligence in people's life is increasing over time. This paper will focus on classification. How to classify efficiently and accurately has become the top priority. In this research, we are trying to use four different algorithms SVM, Naive Bayes, Random Forest, and KNN to classify the text of descriptions. In the experiment, we are going to compare the result of each algorithm by prediction accuracy then summarize the various advantages and disadvantages turns out in each algorithm. The result shows that, the best model we made is Naïve Bayes which can hold for the 55% accuracy in predicting the application number by genre.
Publication Title
2022 IEEE International Conference on Artificial Intelligence and Computer Applications, ICAICA 2022
First Page Number
911
Last Page Number
916
DOI
10.1109/ICAICA54878.2022.9844556
Recommended Citation
Hu, Xinrui and Zhang, Ruiyang, "Text classification based on machine learning" (2022). Kean Publications. 765.
https://digitalcommons.kean.edu/keanpublications/765