Analysis of Adolescent Interests for Vocational Guidance with a Data-Driven Decision Support System

Following their higher education, several students globally struggle to choose a suitable professional route. Adolescents may lack the ability to understand the processes needed to choose a professional route that is right for them. As they progress through this phase, adolescents frequently have questions and concerns regarding their career goals. Additionally, they can doubt their capacity to succeed in their preferred area. Machine learning (ML), a key element of artificial intelligence (Al), is gaining popularity for its ability to assist with individualized vocational guidance by assessing educational history, personal interests, and employment data. Investigation in this area is still uneven and systematically varied despite increased interest. This work used a decision support system (DSS) and ML algorithms to examine adolescent interest in vocational guidance. A comprehensive DSS-based assessment score framework is created employing big data evaluation. Multiple metrics were selected to assess students' literacy and generate DSS and variable matrices. In this study, classification evaluation is used to forecast and evaluate the vocational guidance employing AdaBoost, Support Vector Machine (SVM), and logistic regression (LR). Based on the evaluation results, 58% of students were classified as strong or extremely strong, showing that the vast majority possess the necessary vocational guidance for employment. Students prefer to rate their vocational knowledge higher, with values around 4.1, whereas corporate evaluations average 3.7 points.

Hali tarjima qilinmagan