Repository logo
 

Personality-Based Hybrid Machine Learning Model with Similarity Calculation Algorithm for Mentor-Mentee Matching Using Collaborative and Content Filtering Methods

Files

Thesis(3.12 MB)

Date

2024

Authors

Supervisor

Mohaghegh, Mahsa

Item type

Thesis

Degree name

Master of Computer and Information Sciences

Journal Title

Journal ISSN

Volume Title

Publisher

Auckland University of Technology

Abstract

In the modern corporate environment, the significance of mentoring connections has escalated, acting as a pivotal conduit for both individual and occupational advancement. The present research aims to dissect the pivotal nature and consequences of mentorship bonds within the occupational sphere. It delves into the function that mentorship initiatives play across educational institutions such as high schools and universities, as well as within professional settings, underscoring the importance of matching mentors with mentees through commonalities in interests, knowledge, and objectives. The examination of elements like pedagogical and learning approaches is crucial in fostering a beneficial mentor-mentee dynamic. This inquiry introduces a novel, composite machine learning framework that amalgamates collaborative and content-based filtering techniques to streamline the process of identifying appropriate mentor-mentee couplings, taking into account their abilities, ambitions, and personality archetypes. The scrutiny of skills and objectives enables mentors to adeptly shepherd mentees on their vocational journey, while the assessment of personality traits is instrumental in gauging compatibility and interactive styles. The study culminates by advocating the use of machine learning systems to match mentors with an array of criteria, with an emphasis on personality types as a key parameter for pairing the most congruent mentor and mentee, thereby fostering efficacious mentorship schemes.

Description

Keywords

Source

DOI

Publisher's version

Rights statement

Permanent link

http://hdl.handle.net/10292/17817

Collections

Masters Theses