Skip to main content Skip to navigation

Unlocking Futures: A Natural Language Driven Career Prediction System for Computer Science and Software Engineering Students

Project Overview

The document explores the application of generative AI, specifically a Natural Language Processing (NLP) driven career prediction system, in the context of education for Computer Science (CS) and Software Engineering (SWE) students. It emphasizes the critical need for personalized career guidance that aligns with students' unique skills and interests, facilitating informed decision-making regarding their future careers. By employing machine learning (ML) algorithms to analyze student data, the system aims to accurately predict appropriate career paths, thereby enhancing the effectiveness of academic advisers and career counselors. The findings indicate that such AI-driven tools can significantly improve the quality of career guidance, ensuring that students receive tailored recommendations that reflect their individual capabilities and aspirations. Ultimately, the integration of generative AI in educational settings can lead to more informed career choices, better alignment of student skills with industry demands, and improved outcomes for graduates entering the workforce.

Key Applications

AI-assisted career prediction model using Natural Language Processing

Context: Educational context for undergraduate Computer Science and Software Engineering students

Implementation: Data was collected through Google Forms from various universities and processed using machine learning techniques, including multiple classification algorithms.

Outcomes: The system provides accurate career suggestions based on students' skills, interests, and related activities, helping them navigate career options more effectively.

Challenges: Challenges include ensuring the accuracy of predictions, the quality of data collected, and addressing the complexity of career decision-making.

Implementation Barriers

Data Quality

The quality of data collected through surveys may vary, which can affect the accuracy of predictions.

Proposed Solutions: Implement rigorous data cleaning and preprocessing techniques to ensure data quality and relevance.

Model Complexity

The complexity of machine learning models may lead to issues such as overfitting, affecting their generalization to new data.

Proposed Solutions: Utilize regularization techniques and cross-validation to balance model complexity and performance.

Project Team

Sakir Hossain Faruque

Researcher

Sharun Akter Khushbu

Researcher

Sharmin Akter

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Sakir Hossain Faruque, Sharun Akter Khushbu, Sharmin Akter

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies