A Recruitment System Based on Data Mining: Finding the Best Candidate from Social Media.

As the advancement of network technologies, the recruitment industry is also showing a trend of networking, but the current online recruitment lacks the application of data mining (DM) technology, and its analysis of data is limited to recruitment websites. Therefore, the study proposes a DM-based online recruitment technology that selects the best career candidate through correlation analysis of social media data. The study uses Scrapy crawler to obtain data and utilises an improved Apriori algorithm for correlation analysis. The research findings denote that the proposed algorithm has excellent convergence performance and training efficiency. The study is of experimental design type using experimental data for analysis. In contrast with the traditional Apriori and FP-growth algorithms, the fitting of the output results increases by 6.21% and 14.67%. In addition, the improved algorithm shows significant optimisation effects, with an average running time reduced by 2.44 s and 0.76 s, respectively, compared with the two algorithms, and is less affected by the minimum confidence level. In fit testing, the average error of this method is only 0.02. In summary, online recruitment technology based on DM has strong availability and high reliability. The improved algorithm has excellent performance, accurate output results, and can accurately apply data from social media to select the best job candidate. [ABSTRACT FROM AUTHOR]