An Improved Algorithm for I Bayesian Classification-An Example of Economic News Classification Problem

一種貝氏分類器的改進算法－以經濟新聞分類問題為例

簡春娟(Chuen-Jiuan Jane)

《計量管理期刊》 19卷2期 (2022/11) Pp. 39-48

摘要

In machine learning, Bayesian classifier is based on the application of Bayesian theorem under the assumption of strong independence between features, and is a series of simple probability classifiers. The paper introduces the principle and research purpose of Bayesian algorithm. First, this study analyzes the advantages and disadvantages of algorithms in solving similar problems, then, Bayesian classification is based on a predetermined assumption that when classifying targets, the conditional independence of each keyword must be prioritized, using Bayesian classification Shi's theory must pay attention to the analysis of classification-related theories and classification and coefficient weighting algorithms. Finally, an experimental test is carried out with the economic news classification problem, which proves that the improved algorithm can improve the accuracy of the economic news classification problem.

關鍵字

Economic news ； Keywords ； Bayesian classifier ； Coefficient weighting

並列摘要

貝氏分類器在機器學習中，是基於假設特徵之間強獨立性下貝氏定理的應用，是一系列簡單的概率分類器。本文介紹了貝氏算法的原理和研究的目的。首先，本研究分析了算法在解決類似問題中的優缺點，然後，貝氏分類是基於一個預定的假設，即在對目標進行分類時，必須優先考慮每個關鍵詞的條件獨立性，使用貝氏理論必須注重分類相關理論和分類與係數權重算法的分析。最後，用經濟新聞分類問題進行了實驗測試，證明改進後的算法能夠提高經濟新聞分類問題的準確性。

並列關鍵字

經濟新聞 ； 關鍵詞 ； 貝氏分類器 ； 係數加權

參考文獻

Bayes, theorem, https://en.wikipedia.org/wiki/Bayes%27_theorem. Wiki, Taiwan, 2022.

F. O. López. A bayesian approach to parameter estimation in simplex regression model: a comparison with beta regression, vol. 36, no. 1, pp. 1-21, 2013.

R. F. da Paz, J. L. Bazan, L. A. Milan, Bayesian estimation for a mixture of simplex distributions with an unknown number of components: HDI analysis in Brazil, Journal of Applied Statistics, vol. 44, no. 9, pp. 1630-1643, 2017.

N. M. Ranjan, S. P. Rajesh, Automatic text classification using BPLion-neural network and semantic word processing, The Imaging Science Journal, vol. 66, no. 2, pp. 69-83, 2018.

Y. Y. Li, X. I. Bao, L. C. Jiao, and X. Yu, Partitioned-cooperative quantum-behaved particle swarm optimization based on multilevel thresholding applied to medical image segmentation, Applied Soft Computing, vol. 56, pp. 345-356, 2017.