Research on Personalized Job Recommendation Method Combining Long and Short-term Job Preferences
XU Xiaoying
YE Yi
WAN Shicheng
Abstract：The existing job recommendation methods only consider the long-term preference or short-term preference of us-ers,ignoring the dynamic integration of long-term and short-term preference.Therefore,through the review of domestic and foreign literature on job recommendation methods,this paper proposes a personalized job recommendation method that integrates long-term and short-term job preferences(LSJR).Firstly,the multi-head self-attention mechanism is used to capture the historical interac-tion between the employee and the company,and then the long-term interest expression of the employee is learned.Meanwhile,the recurrent neural network is used to extract the short-term job preference of the employee.Finally,the method uses weighted parame-ters to integrate long-term and short-term job preferences to recommend the company that users may work for next time.The experi-mental results on the real-world employee career data set show that the proposed method is superior to the existing algorithm,which verifies the importance of integrating long and short-term job preferences for personalized job recommendation.
Keywords：job recommendationself-attentive mechanismrecurrent neural networks
Publication Date：2025-09-20
Online Publishing Date：2025-12-23(First online date of this platform, not the publication date of the document)
Pages：6( 2472-2476,2483 )