tailieunhanh - An investigation of Vietnamese document classification

Automatic text classification is one of the most interesting task in data mining. This task has to deal with a huge amount of data. Many studies have been investigated for English, however, the investigation of Vietnamese is still an early stage. This paper investigates several text classification methods: Super Vector Machine, Naive Bayes Classification, K-Nearest Neighbors, Multi-layer perceptron, Decision Tree, Random Forest using TF-IDF. The experiments in Vietnamese datasets show that Super Vector Machine and Multi-layer perceptron perform better than the other methods. |

TỪ KHÓA LIÊN QUAN