Proceedings of the 2nd International Conference on Internet Technology and Educational Informatization, ITEI 2022, December 23-25, 2022, Harbin, China

Research Article

Employment Information Recommendation Model Based on Improved Density Clustering

Download127 downloads
  • @INPROCEEDINGS{10.4108/eai.23-12-2022.2329117,
        author={Guiqin  Duan and Yuxian  Wang and Liying  Guo and Chengsong  Zou},
        title={Employment Information Recommendation Model Based on Improved Density Clustering},
        proceedings={Proceedings of the 2nd International Conference on Internet Technology and Educational Informatization, ITEI 2022, December 23-25, 2022, Harbin, China},
        publisher={EAI},
        proceedings_a={ITEI},
        year={2023},
        month={6},
        keywords={cluster analysis; density clustering; selection of initial cluster center; employment recommendation; education informatization},
        doi={10.4108/eai.23-12-2022.2329117}
    }
    
  • Guiqin Duan
    Yuxian Wang
    Liying Guo
    Chengsong Zou
    Year: 2023
    Employment Information Recommendation Model Based on Improved Density Clustering
    ITEI
    EAI
    DOI: 10.4108/eai.23-12-2022.2329117
Guiqin Duan1, Yuxian Wang1, Liying Guo1, Chengsong Zou1,*
  • 1: Guangdong Songshan Polytechnic
*Contact email: 190352915@qq.com

Abstract

Given employment difficulties and low employment quality of college students under the background of higher vocational enrollment expansion, an employment information recommendation model based on improved density clustering was designed. A weighted user similarity calculation method based on professional similarity, job intention similarity, and professional ability similarity was given, and the quantitative analysis process of professional ability was optimized. Considering that high-density samples are closely surrounded by low-density samples, a new density clustering algorithm was proposed to improve the accuracy of employment recommendations. The practice has proved that this model can effectively mine students’ employment information, and reduce the iteration times of the clustering algorithm, accompanied by high information retrieval integrity and good personalized employment recommendation performance.