关键词: 网络招聘, 虚假招聘广告, 虚假招聘广告检测, 半监督学习, 一致性训练

Abstract: The flood of fake job advertisements will not only damage the legitimate rights and interests of job seekers but also disrupt the normal employment order, which results in a poor user experience for job seekers. To effectively detect fake job advertisements, a semi-supervised fake job advertisements detection model based on consistency training was proposed. The consistency regularization term was used to improve the performance of the model. Supervised loss and unsupervised loss were integrated through joint training to obtain semi-supervised loss. Finally, the semi-supervised loss was used to optimize the model. Experimental results on two real datasets EMSCAD and IMDB show that the proposed model achieves the best detection performance when the labeled data is 20, and the accuracy reaches 70% and 71.7%, respectively. Compared with the existing advanced semi-supervised learning model UDA, the accuracy increased by 2.2% and 2.8% and compared with the deep learning model Bert, the accuracy increased by 3.4% and 11.7% respectively. At the same time, the proposed model had good scalability.

Key words: online recruitment, fake job advertisements, fake job advertisements detection, semi-supervised learning, consistency training