Abstract:
Undergraduate students' intellectual and emotional health are significantly impacted by
mentoring. Having the proper mentor can have a big impact on confidence, motivation, and
long-term goal setting for computer science students, who frequently deal with high levels of
academic pressure and ambiguity about their career trajectory. Nevertheless, conventional
mentor selection techniques fail to consider students' psychological fit with mentors, which
frequently leads to unproductive or brief mentor-mentee relationships. By using a machine
learning-based recommendation system that takes psychological characteristics into account
when choosing mentors, this study seeks to close that gap.
Using well-known models like the Big Five Personality Traits and emotional intelligence
scores, the suggested system integrates psychological profiling. In addition to academic and
technical interests, mentors and students are assessed on their motivational tendencies,
communication preferences, and interpersonal styles. The methodology guarantees improved
emotional alignment and communicative resonance between the mentor and mentee by
including psychological elements in addition to scholastic data.
The model was constructed and trained using machine learning strategies, such as collaborative
filtering and clustering. A psychological compatibility score was incorporated into the
recommendation algorithm, and participant surveys and psychometric testing were used to
create a rich dataset. According to tests, students who were paired with mentors based on
psychological compatibility expressed greater levels of happiness as well as a more robust
sense of belonging and support.
The study also looked at the relationship between mentor-mentee psychological compatibility
and stress levels, academic engagement, and self-efficacy. Pupils who had mentors who shared
their psychological views demonstrated better coping strategies, more academic perseverance,
and more clarity when establishing their career and personal objectives. When mentees were
emotionally open and compatible with their mentoring approach, mentors found it simpler to
offer advice.
An innovative, human-centred method of academic support is introduced by incorporating
psychological concepts into a machine learning-based mentor selection system. This method
meets students' emotional and cognitive demands while also enhancing the caliber of mentoring
relationships. Future studies will examine adaptive learning platforms that modify mentor
recommendations in response to students' academic and psychological development.
