Skip to main content Skip to navigation

AI-Cybersecurity Education Through Designing AI-based Cyberharassment Detection Lab

Project Overview

The document explores the application of generative AI in education, particularly through the development of an AI-based lab aimed at detecting cyberharassment, which engages non-computing students in experiential learning. This innovative approach effectively teaches AI concepts while simultaneously increasing students' knowledge of cyberharassment detection. The findings indicate that combining theoretical instruction with practical, hands-on experience significantly enhances learning outcomes, especially for students who lack prior exposure to AI technologies. By fostering an interactive learning environment, the initiative demonstrates the potential of generative AI to improve educational experiences and outcomes, making complex subjects more accessible and relevant to a broader range of students. Overall, the integration of AI in educational settings not only enriches the learning process but also prepares students to address contemporary issues like cyberharassment through informed, technology-driven solutions.

Key Applications

AI-based Cyberharassment Detection Lab

Context: Educational intervention for non-computing students in Social Statistics courses at North Carolina A&T State University.

Implementation: The lab was designed with a hands-on experiential learning approach, incorporating pre-lab lectures, detailed manuals, and practical tasks using Google Colab.

Outcomes: Students gained moderate to significant improvements in their understanding of AI concepts and cyberharassment detection, with enhanced engagement reported in the Fall semester compared to Spring.

Challenges: Initial lack of student engagement and understanding; terminology confusion; technical difficulties during lab work.

Implementation Barriers

Engagement and Content Understanding Barrier

Students initially struggled with engagement and understanding the lab content due to their lack of prior knowledge in AI and found the terminology and concepts challenging, leading to confusion.

Proposed Solutions: Incorporating pre-lab lectures, improving the clarity and detail of lab instructions, simplifying the terminology used in the lab materials, and providing extensive explanations.

Technical Barrier

Students faced difficulties with technical issues and errors during the lab exercises.

Proposed Solutions: Providing troubleshooting steps in the lab manual and considering in-person lab sessions for better guidance.

Project Team

Ebuka Okpala

Researcher

Nishant Vishwamitra

Researcher

Keyan Guo

Researcher

Song Liao

Researcher

Long Cheng

Researcher

Hongxin Hu

Researcher

Yongkai Wu

Researcher

Xiaohong Yuan

Researcher

Jeannette Wade

Researcher

Sajad Khorsandroo

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Ebuka Okpala, Nishant Vishwamitra, Keyan Guo, Song Liao, Long Cheng, Hongxin Hu, Yongkai Wu, Xiaohong Yuan, Jeannette Wade, Sajad Khorsandroo

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