<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In the face of a large amount of news text information, how to make a reasonable classification of news text is a hot issue of modern scholars. To solve the problem that only word co-occurrence was considered in the Text Graph Convolutional Network (Text-GCN) method to build a graph model, a news text classification algorithm which fuses themes and is based on Graph Convolution Network, is presented. Firstly, the LDA topic model is used to process the corpus to obtain the distribution of themes of the corpus. Secondly, a graph model is built to construct a global map by using the related topic words and their subject distribution in each article. Finally, the text graph is input into the Graph Convolution Network layers to compute the learning representation of combining feature in order to complete the text classification task. The experimental results show that this method can effectively realize the word level interaction of information in text. In the experiment on Chinese and English datasets, adding theme information improves the accuracy by 1% compared with the Text-GCN method.</p>
</abstract>

In the face of a large amount of news text information, how to make a reasonable classification of news text is a hot issue of modern scholars. To solve the problem that only word co-occurrence was considered in the Text Graph Convolutional Network (Text-GCN) method to build a graph model, a news text classification algorithm which fuses themes and is based on Graph Convolution Network, is presented. Firstly, the LDA topic model is used to process the corpus to obtain the distribution of themes of the corpus. Secondly, a graph model is built to construct a global map by using the related topic words and their subject distribution in each article. Finally, the text graph is input into the Graph Convolution Network layers to compute the learning representation of combining feature in order to complete the text classification task. The experimental results show that this method can effectively realize the word level interaction of information in text. In the experiment on Chinese and English datasets, adding theme information improves the accuracy by 1% compared with the Text-GCN method.

Research on Topic Fusion Graph Convolution Network News Text Classification Algorithm

School of Computer Science and Technology

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

In the face of a large amount of news text information, how to make a reasonable classification of news text is a hot issue of modern scholars. To solve the...

Dataset	Total_docs	Training_docs	Testing_docs	Total_words	Categories
20NewsGroup	18,846	13,192	5,654	42,739	20
AGNews	8,000	5,600	2,400	32,653	4
CH_News	1,080	756	324	13,324	5

DataSets	20newsgroup	AGNews	Ch_News
Model	20newsgroup	AGNews	Ch_News
SVM+LDA	0.6827	0.7241	0.6956
CNN	0.7160	0.8059	0.6893
Text-GCN	0.8634	0.9245	0.7402
LDA-THG+GCN	0.8796	0.9310	0.7594

Research on Topic Fusion Graph Convolution Network News Text Classification Algorithm

Data publikacji: 24 maj 2023

Zakres stron: 90 - 100

DOI: https://doi.org/10.2478/ijanmc-2022-0030

Słowa kluczowe
Text Graph Convolutional Network, Graph Convolutional Network, Latent Dirichlet Allocation Topic Model(LDA topic model), Graph Model

© 2022 Li Liu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Statistical table of data sets used in experiments

Comparison of experimental results

Research on Topic Fusion Graph Convolution Network News Text Classification Algorithm

Data publikacji: 24 maj 2023

Zakres stron: 90 - 100

DOI: https://doi.org/10.2478/ijanmc-2022-0030

Słowa kluczoweText Graph Convolutional Network, Graph Convolutional Network, Latent Dirichlet Allocation Topic Model(LDA topic model), Graph Model

© 2022 Li Liu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Statistical table of data sets used in experiments

Comparison of experimental results

Słowa kluczowe
Text Graph Convolutional Network, Graph Convolutional Network, Latent Dirichlet Allocation Topic Model(LDA topic model), Graph Model