Otkrivanje mekih vještina iz životopisa zadanih u slobodnom obliku

master's thesis

• Title (english): Extraction of Soft Skills from Free-form Resumes
• Author: Karlo Butorac
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Klemo Vladimir (član povjerenstva)
• Committee member: Goran Delač (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Tema ovog diplomskog rada je otkrivanje mekih vještina iz životopisa zadanih u slobodnom obliku. U radu su opisane meke vještine i njihova važnost u profesionalnom svijetu. Dvije aplikacije napravljene su za potrebe rada - jedna za označavanje podataka i jedna za otkrivanje mekih vještina. U svrhu otkrivanja mekih vještina korištena je metoda obrade prirodnog jezika. Opisana je i povijest obrade prirodnog jezika, te su definirani modeli strojnog učenja korišteni u radu. Korišteni modeli strojnog učenja su povratne neuronske mreže i ćelije sa dugoročnom memorijom. Uspoređeni su i vrednovani rezultati korištenih modela strojnog učenja.

Abstract (english)

The subject of this master's thesis is the extraction of soft skills from free-form resumes. The paper describes soft skills and their importance in the professional world. For the needs of the paper, an application for data marking and an application for the extraction of soft skills were both created. The discovery and extraction of soft skills were made using natural language processing. The paper contains a summary of the history of natural language processing and the definitions of machine learning models used. Models used are recurrent neural networks and long short-term memory networks. The results of the used machine learning models were compared and evaluated.

• Keywords: Obrada prirodnog jezika; meke vještine; životopis; strojno učenje; analiza teksta; rudarenje podataka; povratne neuronske mreže; ćelija sa dugoročnom memorijom; RNN; LSTM
• Keywords (english): Natural language processing; soft skills; resume; machine learning; text analysis; data mining; recurrent neural networks; long short-term memory; RNN; LSTM
• Language: croatian
• URN:NBN: urn:nbn:hr:168:064287
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 11:56:22