A Resume Recommendation Algorithm Based on K-means++ and Part-of-speech TF-IDF
Liting Duan, Xiaolin Gui, Mingan Wei, You Fu Wu · 2019
This paper proposes a personalized resume recommendation algorithm in order to help job seekers find the right job and enterprises find the right talents. Firstly, we extracted resume feature and used K-means++ algorithm to cluster positions. The use of clustering results is beneficial for speedy recommendation. Afterward, we also constructed text vector and combined TF-IDF and part-of-speech weights to recommend resumes. At last, it is proved that the recommendation result of the proposed algorithm is better than the word frequency vector after a lot of manual evaluations.