Mining Labor Market Requirements Using Distributional Semantic Models and Deep Learning

Botov, Dmitriy; Klenin, Julius; Melnikov, A.; Dmitrin, Yuri; Nikolaev, Ivan; Vinel, Mikhail

doi:10.1007/978-3-030-20482-2_15

Cited by 31 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some authors use knowledge graphs indicating the co-occurrence of raw terms ( Jia et al, 2018 ; Giabelli et al, 2020 ; Börner et al, 2018 ; Colace et al, 2019 ; Boselli et al, 2018 ). The others apply descriptions of skills from national occupational classifiers ( Cao et al, 2021 ; Colombo, Mercorio & Mezzanzanica, 2019 ; Karakatsanis et al, 2017 ; Lovaglio et al, 2018 ; Botov et al, 2019 ; Amato et al, 2015 ). The rest—use manual mark-up for extracted knowledge domains ( Calanca et al, 2019 ; Sayfullina, Malmi & Kannala, 2018 ; Hoang et al, 2018 ).…”

Section: Related Workmentioning

confidence: 99%

“…The other existing studies use both “soft” and “hard” skills. Some authors analyze mixed skill sets but without distinction between their types ( Colace et al, 2019 ; Karakatsanis et al, 2017 ; Lovaglio et al, 2018 ; Botov et al, 2019 ; Boselli et al, 2018 ; Amato et al, 2015 ; Jia et al, 2018 ; Börner et al, 2018 ; Pejic-Bach et al, 2020 ; Litecky et al, 2009 ; Poonnawat, Pacharawongsakda & Henchareonlert, 2017 ; Xu et al, 2018 ; Wowczko, 2015 ; Fareri et al, 2020 ; Bensberg, Buscher & Czarnecki, 2019 ; Ternikov & Aleksandrova, 2020 ; Verma et al, 2019 ). Another group of papers provides separation in two ways.…”

Section: Related Workmentioning

confidence: 99%

“…Some authors use job titles and their descriptions from vacancies in order to match them with ESCO (European Skills/Competences, qualifications and Occupations), ISCO (International Standard Classification of Occupations), or O*NET (Occupational Information Network) classifiers ( Boselli et al, 2018 ; Cao et al, 2021 ; Colombo, Mercorio & Mezzanzanica, 2019 ; Lovaglio et al, 2018 ; Colace et al, 2019 ; Papoutsoglou, Mittas & Angelis, 2017 ; Giabelli et al, 2020 ). Others use the structure of job advertisements provided on hiring platforms and validate it with domain experts mark-up and professional standards ( Chang, Wang & Hawamdeh, 2019 ; Ternikov & Aleksandrova, 2020 ; Hiranrat & Harncharnchai, 2018 ; Amato et al, 2015 ; Sayfullina, Malmi & Kannala, 2018 ; Litecky, Igou & Aken, 2012 ; Hoang et al, 2018 ; Botov et al, 2019 ; Brooks, Greer & Morris, 2018 ). This research employs text mining techniques such as TF-iDF and n -grams that are used for specific words and phrases extraction.…”

Section: Related Workmentioning

confidence: 99%

“…Accordingly, text mining techniques are widely applied for the identification of core competencies. Thirdly, the data obtained from hiring platforms are matched with official classifiers for occupations and skills and then unified with labor market representation ( Amato et al, 2015 ; Botov et al, 2019 ; Boselli et al, 2018 ; Colombo, Mercorio & Mezzanzanica, 2019 ; Lovaglio et al, 2018 ). Existing studies use several open-source databases with processed “soft” and “hard” skills for the mentioned tasks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Soft and hard skills identification: insights from IT job advertisements in the CIS region

Ternikov

2022

PeerJ Computer Science

View full text Add to dashboard Cite

Labor market transformations significantly affect the sphere of information technologies (IT) introducing new instruments, architectures, and frameworks. Employers operate with new knowledge domains which demand specific competencies from workers including combinations of both technical (“hard”) and non-technical (“soft”) skills. The educational system is now required to provide the alumni with up-to-date skill sets covering the latest labor market trends. However, there is a big concern about the self-adaptation of educational programs for meeting the companies’ needs. Accordingly, frequent changes in job position requirements call for the tool for in-time categorization of vacancies and skills extraction. This study aims to show the demand for skills in the IT sphere in the Commonwealth of Independent States (CIS) region and discover the mapping between required skill sets and job occupations. The proposed methodology for skills identification uses natural language processing, hierarchical clustering, and association mining techniques. The results reveal explicit information about the combinations of “soft” and “hard” skills required for different professional groups. These findings provide valuable insights for supporting educational organizations, human resource (HR) specialists, and state labor authorities in the renewal of existing knowledge about skill sets for IT professionals. In addition, the provided methodology for labor market monitoring has a high potential to ensure effective matching of employees.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Soft and hard skills identification: insights from IT job advertisements in the CIS region

Ternikov

2022

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Similarly, [53] used word2vec embeddings [54] to compute the similarity between skills cited in job ads and professional standards. The latter are a set of practices, ethics, and behaviors to which members of a particular professional group must adhere.…”

Section: ) Skill Embeddingmentioning

confidence: 99%