Integrating technological innovations with advances in vocational interest research: Development of a career guidance chatbot prototype

Chu, Chu

Permalink

https://hdl.handle.net/2142/125596 Copy

Description

Title

Integrating technological innovations with advances in vocational interest research: Development of a career guidance chatbot prototype

Author(s)

Chu, Chu

Issue Date

2024-07-10

Director of Research (if dissertation) or Advisor (if thesis)

Rounds, James

Doctoral Committee Chair(s)

Rounds, James

Committee Member(s)

• Oswald, Frederick
• Fraley, Chris
• Zhang, Bo
• Hoff, Kevin
• Sun, Tianjun

Department of Study

Psychology

Discipline

Psychology

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• Vocational Interests
• Measurement
• Chatbot
• Natural Language Processing
• Large Language Models
• Machine Learning
• Career Guidance

Abstract

Under the background of job market turmoil and rapid advancements in technology, there is an increasing need for career guidance amongst U.S. workers. This dissertation advances the field of vocational interest measurement in the context of career counseling by building three sets of tools that are designed to work together for assessing person-occupation (P-O) fit through chat-based text data. Study 1 presents the Comprehensive Assessment of Basic Interests—O*NET (CABIN-NET), a survey instrument connecting basic interests with ONET’s occupational knowledge variables for assessing P-O fit. Study 2 Part 1 details the design of the Career Guidance Chatbot (CGC-bot), an AI-powered conversational agent that collects diverse, valuable work preference information from users. Lastly, Study 2 Part 2 leverages Natural Language Processing (NLP) & Machine Learning (ML) techniques for building twenty machines that effectively predict basic interest scores from users’ chat history with the CGC-bot. Subsequently, these machine-predicted scores were connected to the O*NET data through the CABIN-NET framework, ultimately offering suitable O*NET occupation suggestions. Therefore, this dissertation provides innovative and useful tools for people who need efficient yet detailed career guidance. Furthermore, this work sets the benchmark for future research that aims to measure vocational interest with non-traditional data types, and it paved paths for numerous research fronts for advancing interest measurement in the new era.

Graduation Semester

2024-08

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/125596

Copyright and License Information

Copyright 2024 Chu Chu

Owning Collections