kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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
ChatGPT: A replacement of copywriters in the work of creating resumes
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2024 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

This exploratory study investigates whether ChatGPT can produce high quality role descriptions for resumes within the IT-consultancy sector, and was conducted at the IT-consultancy company Skry. The methodology involved semi-structured interviews with 6 individuals experienced in evaluating such textual content, who evaluated three role descriptions each from ChatGPT and a copywriter to assess the text's quality. The findings indicate that ChatGPT has the capability to produce high quality role descriptions that are comparable in quality to those produced by a copywriter. Specifically, ChatGPT's role descriptions received higher average ratings in two out of three cases when compared to those written by a copywriter, although the highest-rated description overall was created by a copywriter. The study also highlights differences in the characteristics of role descriptions produced by ChatGPT and a copywriter. The key difference between them proved to be that ChatGPT's role descriptions were often perceived as too formal, whereas the copywriter's texts were considered somewhat informal. These insights could benefit companies like Skry, which seeks to streamline their role description creation process, and pave the way for future research in the application of ChatGPT within Human Resources Management (HRM). This research builds on existing literature exploring the potential and advantages of AI tools like ChatGPT in HRM. Due to the study's limited participant pool and the comparison with texts from only one individual, broader conclusions cannot be drawn.

Abstract [sv]

Denna utforskande studie undersöker om ChatGPT kan producera högkvalitativa rollbeskrivningar för meritförteckningar inom IT-konsultsektorn och genomfördes på IT-konsultföretaget Skry. Metodiken involverade semistrukturerade intervjuer med 6 individer med erfarenhet av att utvärdera liknande textinnehåll, som utvärderade tre rollbeskrivningar vardera från ChatGPT och en copywriter för att bedöma texternas kvalitet. Resultaten indikerar att ChatGPT har förmågan att producera högkvalitativa rollbeskrivningar som är jämförbara i kvalitet med de som produceras av en copywriter. Närmare bestämt fick ChatGPT:s rollbeskrivningar högre genomsnittligt betyg i två av tre fall jämfört med de skrivna av en copywriter, även om den högst rankade beskrivningen totalt sett skapades av en copywriter. Studien lyfter också fram skillnader i egenskaperna hos rollbeskrivningar producerade av ChatGPT och en copywriter. Den viktigaste skillnaden mellan dem visade sig vara att ChatGPT:s rollbeskrivningar ofta uppfattades som alltför formella, medan copywriterns texter ansågs vara något informella. Dessa insikter kan gynna företag som Skry, som vill effektivisera sin process för att skapa rollbeskrivningar och bana väg för framtida forskning inom tillämpningen av ChatGPT inom Human Resources Management (HRM). Denna forskning bygger på befintlig litteratur som utforskar potentialen och fördelarna med AI-verktyg som ChatGPT inom HRM. På grund av studiens begränsade deltagargrupp och jämförelsen med texter från endast en individ, kan bredare slutsatser inte dras.

Place, publisher, year, edition, pages
2024. , p. 11
Series
TRITA-EECS-EX ; 2024:214
Keywords [en]
ChatGPT, ChatGPT-3.5, OpenAI, Human Resources Management, HRM, Resumes, CV, Role description, Valence
Keywords [sv]
ChatGPT, ChatGPT-3.5, OpenAI, Personalledning, HRM, Meritförteckningar, CV, Rollbeskrivning, Valens
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-349246OAI: oai:DiVA.org:kth-349246DiVA, id: diva2:1880181
Supervisors
Examiners
Available from: 2024-08-08 Created: 2024-06-30 Last updated: 2024-08-08Bibliographically approved

Open Access in DiVA

fulltext(897 kB)191 downloads
File information
File name FULLTEXT01.pdfFile size 897 kBChecksum SHA-512
304ba0cd2cafe53ab0cafb706ffcd2841c151cae41d731c4d59b9b0ed66bf2d86a0122facdfedc63e7551785c0b9d6b8d3e4fc5221044bc89a085413755f810e
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 191 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: 537 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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