Research Article
Evaluation of E-bike Safety Management Policy Based on Text Mining
@INPROCEEDINGS{10.4108/eai.1-9-2023.2338797, author={Enhua Zhang and Weijie Wang and Tingli Zhao and Dong Chen}, title={Evaluation of E-bike Safety Management Policy Based on Text Mining}, proceedings={Proceedings of the 2nd International Conference on Public Management, Digital Economy and Internet Technology, ICPDI 2023, September 1--3, 2023, Chongqing, China}, publisher={EAI}, proceedings_a={ICPDI}, year={2023}, month={11}, keywords={traffic management e-bikes sentiment classification text feature extraction lda topic model}, doi={10.4108/eai.1-9-2023.2338797} }- Enhua Zhang
Weijie Wang
Tingli Zhao
Dong Chen
Year: 2023
Evaluation of E-bike Safety Management Policy Based on Text Mining
ICPDI
EAI
DOI: 10.4108/eai.1-9-2023.2338797
Abstract
In view of the public comments on the safety management policy of electric bicycle on Weibo, this paper obtained the text data of related comments through crawler. snownlp and TF-IDF were used to conduct emotion mining and text feature extraction on the text data, and the LDA topic model of negative text was constructed to analyze the potential topic keywords of negative emotion. The results show that within one year after the implementation of Jiangsu E-bikes Management Regulations, positive and negative emotions account for almost the same proportion in Weibo comments, and the focus of both are “mandatory helmets using” and “prohibition of carrying adults”. Those with positive attitudes believe that mandatory helmet using and prohibition of carrying adults can improve safety of e-bike riding. The main reasons for the negative attitude were: prohibition of carrying adults, the rose price of helmets, inconvenient to carry helmets, wearing helmets when riding shared e-bikes and replacing with construction helmets. This study provides an effective tool for safety management policy evaluation and analysis of electric bicycles.