Data-Driven Job Search Engine Using Skills and Company Attribute Filters

In this article we compare different vector models (tf-idf, word2vec, fasttext, lda, lsi, artm) in the short text clustering task, using a dataset of job vacancy descriptions in Russian. A two-step experiment is proposed to determine the best model and its hyperparameters based on the quality of the resulting short text clusters. In the first stage, we investigate how various hyperparameters of each model can affect the clusters, produced by training a K-means model on each of the vector representations. In particular, we consider in detail, how the size of the output vector representation in each of our models can influence the quality of the final clusters. We also provide an extensive analysis of the effects of various regularization options for clusters, learned using the vectors produced by the ARTM algorithm. During the second stage, the models showing the best results in the previous step (word2vec, fasttext) are analyzed in greater detail. We compare the effectiveness of these models against datasets of different sizes, as well as using different structures of the source fragments (partial elements or full texts of vacancy descriptions). In our experiments, the highest quality of clusters (evaluated using the ARI metric) was achieved by word2vec, closely followed by the fasttext model. Finally, we perform a topic analysis for each of the resulting clusters and evaluate their homogeneity.

show abstract

“…New approaches to analysis and short texts in general [6,8] and labor market texts in particular [9,13] are currently being actively developed.…”

Section: Discussionmentioning

confidence: 99%

The Comparison of Distributive Semantics Models Applied to the Task of Short Job Requirements Clustering for the Russian Labor Market

Nikolaev¹,

Ryazanov²,

Botov³

2020

Proceedings of the 8th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2020)

View full text Add to dashboard Cite

show abstract

“…Many studies built recommendation systems for jobs and MOOCs using the skills identified from job ads. In [130], the authors presented a data-driven job search engine. This consists of comprehensive search filters including user skill set-focused attributes and various company attributes.…”

Section: ) Job and Mooc Recommendationmentioning

confidence: 99%

A Survey on Skill Identification From Online Job Ads

2021

View full text Add to dashboard Cite

show abstract

“…The result shows that there is a substantial overlap between the entities extracted from job advertisements and the entities extracted from developer profiles and the linear correlation between the number of times a concept appears in developer profiles vs job adverts is r=0.49. In more recent work, Muthyala et al [10] discussed a methodology that improves user job searching experience by adding skill set and company attribute filters. The TF-IDF weighting is used to calculate the frequencies for all unique skills of the document itself.…”

Section: Literature Reviewmentioning

confidence: 99%

Jobseeker-industry matching system using automated keyword selection and visualization approach

Kamaruddin

Rahman

Lawi

2019

IJEECS

View full text Add to dashboard Cite

Learning opportunities are available with the accessibility of new learning technologies, discovery of untraditional learning pathways and awareness of the importance of connecting current knowledge with new learning. Such situation allows the expansion in the number of courses, programs and professional certifications offered to the students resulting to the increment of the number of graduates annually. The graduates then employed by the industry for executing the job. However, there is a growing concern about the increment of unemployed graduates in the job market. One of the reasons of the mismatch between graduates’ skills and employers’ needs is that the jobseekers tend to choose wrong job because they are overwhelmed by the choices and typically they just randomly send the application because it is time consuming to filter relevant advert. Such action may have repercussion to the industry because the employers need to select relevant candidates to fill up the post from the unfiltered pile of applications making the selection process lengthy and time consuming. In this paper we proposed an automated approach to match the graduates’ and employers’ needs using a hybrid of text mining and visualization approach to facilitate jobseekers’ task of relevant job application. The important keywords are automatically extracted based on the frequency of the word used in the adverts. Then, the graduates’ skills are matched from their personalized profile. Relevant visualization approaches are incorporated to facilitate the selection. It is practical and feasible for the proposed approach to be incorporated in job searching websites that can optimize jobseekers and employers time and effort for a suitable match.

show abstract

Data-Driven Job Search Engine Using Skills and Company Attribute Filters

Cited by 15 publications

References 12 publications

The Comparison of Distributive Semantics Models Applied to the Task of Short Job Requirements Clustering for the Russian Labor Market

The Comparison of Distributive Semantics Models Applied to the Task of Short Job Requirements Clustering for the Russian Labor Market

A Survey on Skill Identification From Online Job Ads

Jobseeker-industry matching system using automated keyword selection and visualization approach

Contact Info

Product

Resources

About