A Vectorization Model for Job Matching Application of a Government Employment Service Office
Abstract—The fast growth of the Internet caused a matching growth of the amount of available online information that increased the need to expand the ability of users to manage all this information. This encourages a substantial interest in specific research fields and technologies that could benefit the managing of this information overload. However, in the Philippines, it has been a challenge for most job agencies to find out and predict job matching intelligently due to lack of accurate models to be adopted. To address this problem, the researchers developed job matching application specifically for Pangasinan Employment Service Office (PESO). The aim is to know how these measures behave and whether they validate the idea that applicants‟ data have more in common with job profile. The process of matching an applicant with an offered job is performed through the use of vectorization model and cosine similarity. Large training sets of records of applicants and job profiles were used to define the weights of the parameters. The results show that the selection of cosine similarity measures and vector weights are significant in job matching application, especially in those where the applicants‟ information‟s likeness is measured.
Index Terms—Vector space model, job matching application, cosine similarity, resumes
Leah G. Rodriguez, Christopher A. Rodriguez
Pangasinan State University, PHILIPPINES
Enrico P. Chavez
Technological Institute of the Philippine, PHILIPPINES
Cite: Leah G. Rodriguez, Enrico P. Chavez, Christopher A. Rodriguez, "A Vectorization Model for Job Matching Application of a
Government Employment Service Office," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 32-36, Hong Kong, 15-17 June, 2019.