Research Article
Urban Governance Information Classification Method Based on BERT-TextCNN
@INPROCEEDINGS{10.4108/eai.26-5-2023.2334281, author={Jun Wu and Tianyi Li and Xinli Zheng}, title={Urban Governance Information Classification Method Based on BERT-TextCNN}, proceedings={Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26--28, 2023, Nanjing, China}, publisher={EAI}, proceedings_a={MSEA}, year={2023}, month={7}, keywords={bert textcnn text classification urban governance information}, doi={10.4108/eai.26-5-2023.2334281} }- Jun Wu
Tianyi Li
Xinli Zheng
Year: 2023
Urban Governance Information Classification Method Based on BERT-TextCNN
MSEA
EAI
DOI: 10.4108/eai.26-5-2023.2334281
Abstract
In view of the existing Word2Vec traditional word vector model cannot solve the problem of text context semantics, this paper proposes a network model BERT-TextCNN for text classification of urban governance information based on the combination of BERT pre-training model and multi-scale convolution kernel TextCNN convolution neural network. The model obtains text context information more efficiently through rich convolution kernel combination. Through experiments in the urban governance information text data set, the experimental results show that the accuracy rate, recall rate and Micro-F1 value of the model have reached more than 90%, which can effectively improve the classification effect of urban governance information text.
