Research Experiment on Multi-Model Comparison for Chinese Text Classification Tasks

TL;DR

This paper compares the performance of three deep learning models—TextCNN, TextRNN, and FastText—in Chinese text classification tasks using the THUCNews dataset, providing insights into their suitability for various scenarios.

Contribution

It offers a systematic comparison of deep learning models for Chinese text classification, highlighting their strengths and limitations in different contexts.

Findings

TextCNN achieves the highest accuracy among the models.

FastText is the fastest in training and inference.

Model performance varies depending on the classification scenario.

Abstract

With the explosive growth of Chinese text data and advancements in natural language processing technologies, Chinese text classification has become one of the key techniques in fields such as information retrieval and sentiment analysis, attracting increasing attention. This paper conducts a comparative study on three deep learning models:TextCNN, TextRNN, and FastText.specifically for Chinese text classification tasks. By conducting experiments on the THUCNews dataset, the performance of these models is evaluated, and their applicability in different scenarios is discussed.