AUTHOR=Kong Yinying , Huang Niangqiu , Deng Haodong , Feng Junwen , Liang Xingyi , Lv Weisi , Liu Jingyi 

TITLE=Text classification in fair competition law violations using deep learning

JOURNAL=Frontiers in Applied Mathematics and Statistics

VOLUME=Volume 9 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/applied-mathematics-and-statistics/articles/10.3389/fams.2023.1177081

DOI=10.3389/fams.2023.1177081

ISSN=2297-4687

ABSTRACT=Ensuring fair competition through manual review poses significant challenges. This paper proposes the utilization of LSTM (Long Short-Term Memory) neural network and TextCNN (Convolutional Neural Network) to establish a text classifier for classifying and reviewing normative documents. The experimental dataset comprises policy measure samples provided by the antitrust division of the Guangdong Market Supervision Administration. The study compares the performance of LSTM and TextCNN classification models. The experimental results of the classification review demonstrate that, in three classification experiments without an enhanced experimental dataset, the LSTM classifier achieved an accuracy of 95.74%, while the TextCNN classifier achieved 92.7% accuracy on the test set. In contrast, for three classification experiments utilizing an enhanced experimental dataset, the LSTM classifier achieved an accuracy of 96.36%, while the TextCNN classifier achieved 96.19% accuracy on the test set.