Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
EVALUATING FEATURE EXTRACTION METHODS FOR AUTOMATED APPLICANT-COMPANY CONNECTIONS
Umeå University, Faculty of Science and Technology, Department of Computing Science.
2024 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

This thesis explores the use of various Natural Language Processing (NLP) methods of automated matching between job seekers and potential employers. In the study, two different text representation techniques are evaluated, sentence embeddings and character n-gram. Keyword extraction using KeyBERT is investigated as a potential enhancement to this matching process. Additionally, cosine similarity and L1 distance are compared to understand which similarity metric is best for the task. Using a dataset of 482 CVs and 63 companies, the research investigates the effectiveness of these methods in capturing the nuances of job titles and applicants' profiles. The results indicate that sentence embeddings on the full text of a CV using cosine similarity perform the best for this task in terms of accuracy. The findings highlight the challenges of aligning the CV content with specific job titles sought by companies. The study's contribution includes identifying the optimal feature extraction method for automated applicant-company matching and highlighting the limitations of keyword extraction in this context.

Place, publisher, year, edition, pages
2024. , p. 26
Series
UMNAD ; 1473
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:umu:diva-226995OAI: oai:DiVA.org:umu-226995DiVA, id: diva2:1876202
External cooperation
Atea Sverige AB; Boden Kommun
Educational program
Bachelor of Science Programme in Computing Science
Supervisors
Examiners
Available from: 2024-06-26 Created: 2024-06-24 Last updated: 2024-06-26Bibliographically approved

Open Access in DiVA

fulltext(2347 kB)137 downloads
File information
File name FULLTEXT01.pdfFile size 2347 kBChecksum SHA-512
6e0be9898d60e494d777000ab3f4cdb9cf5ec329f6c213b49585b894f64a7f9de59d355a27f97bcee5725d807cad2754bfcf83bc1157170e77f6d221897eaf03
Type fulltextMimetype application/pdf

By organisation
Department of Computing Science
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 137 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 348 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf