Introducing AI in Academia (3 of 4): Using AI to Enhance Learning

Opportunities and Challenges of AI in Education

This is the third in a series of blog posts written by the Artificial Intelligence Faculty Learning Community Group (AI FLC) at Regis College. Although the posts are primarily intended for the Regis community, the conversation is open to everyone. This post was written by Allen Karsina.

AI in Academia

Welcome back! In our previous posts, we identified five key topics that deserve thoughtful discussion:

NotebookLM Audio Overview of this Post

0:00

1. What is AI?

2. How is AI currently being used in education?

3. What are the benefits and opportunities of integrating AI into education?

4. What are the challenges and risks of integrating AI into education?

5. What are the best practices for integrating AI into education?

We have explored the first two questions, and so in this post we will now tack the next two questions, taking a look at both the potential benefits and risks of integrating AI into education as well as the challenges and risks.

Benefits and Opportunities of Integrating AI into Higher Education

As we consider the potential benefits and opportunities of integrating AI into higher education, it is important to acknowledge that many of these advancements remain aspirational. Whether AI will truly "transform" education or whether the changes will fall short of expectations is still an open question. Moreover, each of these potential benefits comes with its own set of risks and challenges, which I will also address in this post.

To present the benefits and opportunities, I utilized the Notebook in NotebookLM from my previous post and provided the prompt: Give me the five main benefits and opportunities of integrating AI into higher education, with an example of each benefit/opportunity.

Here is the response from NotebookLM, with some minor formatting adjustments:

Integrating AI into higher education offers numerous benefits and opportunities, including personalized learning, enhanced feedback and assessment, improved accessibility and inclusivity, transformed teaching and learning, and specific AI applications.

Personalized and Adaptive Learning: AI can tailor educational experiences to individual student needs, with systems adjusting the difficulty of lessons or offering specific support. For example, if a student struggles with photosynthesis, an AI system could extend the topic by adding extra resources and lessons. AI can also personalize learning through analysis of vast datasets, offering comprehensive and contextually relevant content in real-time.

Enhanced Feedback and Assessment: AI can provide immediate, nuanced, and personalized feedback, which can help students understand mistakes and rectify them promptly. For example, AI can analyze a student's essay and provide real-time feedback on grammatical errors or suggest improvements to their arguments, which can enhance learning and continuous improvement. Additionally, AI can automate routine grading tasks, reducing the workload for instructors and allowing them to focus on more complex aspects of teaching.

Improved Accessibility and Inclusivity: AI can ensure that educational resources and opportunities are available to diverse student populations. For example, AI-powered virtual assistants like ChatGPT can provide 24/7 support to students, including those in remote areas or those who need additional support, as well as create a learning environment that promotes inclusivity for students with special needs. Additionally, AI can help bridge digital disparities by ensuring equal access to technology and educational resources.

Transforming Teaching and Learning: AI can enhance the learning environment by making it more engaging and interactive. For example, AI-driven platforms can facilitate supportive and intuitive interactions with users, such as using an AI tutor in a virtual learning environment to provide students with personalized academic guidance, feedback, and relevant resources. AI can also help to redefine the role of educators, allowing them to focus on the human aspects of teaching, such as mentorship and sparking curiosity. AI can further promote critical thinking skills and prepare students for collaborative AI environments in their professional lives.

Specific AI Applications: Various AI tools can be implemented to improve higher education, including generative AI, large language models, and AI-powered chatbots. For example, generative AI can create diverse and contextually relevant content, such as quizzes and learning materials, while large language models can enhance educational dialogues and assist with complex subjects. AI chatbots can serve as virtual assistants that provide real-time support, personalized guidance, and assistance to students.

Overall, AI offers a variety of tools and capabilities that can be used to create more personalized, engaging, and accessible learning experiences within higher education.

Overall, NotebookLM provided a solid overview of the potential benefits of AI in education. One additional benefit, albeit more aspirational, involves integrating the Internet of Things (IoT) into higher education. Smart classrooms equipped with interconnected devices could seamlessly transfer data, enabling effortless collaboration between educators and students. Autonomous systems might regulate classrooms and living spaces, adjusting temperature and lighting automatically. Additionally, data collected from devices and sensors could support the development of personalized learning curricula, suggest campus activities tailored to individual interests, and much more.

Interactive Activity. Copy and paste this prompt into Copilot or ChatGPT. Give me a multiple choice quiz question about the benefits and uses of AI in the classroom. Wait until I answer the question to respond. If I answer the question correctly, provide praise. If I answer the question incorrectly, give me the correct answer and explain why it is correct. Then ask me another multiple choice question. Stop when I ask you to stop.

If you do the interactive activity above, you may find some additional prompting is needed for an optimal experience. ChatGPT has a tendency to give you all of the questions and answers at once, for example, even when you ask it not to in your original prompt. Just tell the AI what you want, and you should get there.

Risks and Challenges of Integrating AI into Higher Education

Now that we have explored the benefits and opportunities, let’s turn to the risks and challenges. To guide this discussion, I utilized the Notebook in NotebookLM from my previous post and provided the following prompt: Give me the five main risks and challenges of integrating AI into higher education, with an example of each risk/challenge.

Here is the response from NotebookLM, with some minor formatting adjustments:

Integrating AI into higher education presents several risks and challenges that must be carefully considered. These include the potential for over-reliance on AI, accuracy concerns and the spread of misinformation, the loss of the personal touch in education, challenges to academic integrity, and resource and equity issues.

Over-reliance on AI: One of the main risks is that students may become overly dependent on AI tools, which could diminish their independent research and critical thinking skills. For example, if students rely on AI to generate research summaries or complete writing assignments, they may not develop their own abilities to analyze and synthesize information, thus affecting their preparedness for real-world challenges and post-academic pursuits. Over-reliance on AI can also lead to a neglect of essential skills such as creative thinking and problem solving.

Accuracy Concerns and Misinformation: There is a risk that AI systems may provide inaccurate or biased information, which can mislead students and reduce the overall quality of education. For instance, if an AI chatbot generates incorrect answers to a student's query, the student may not realize the error and incorporate it into their understanding, leading to a misunderstanding of the topic. Additionally, generative AI can propagate misinformation, as AI can mass-produce questionable content.

Loss of Personal Touch: The integration of AI may lead to a reduction in human interaction within the educational process. For example, if AI-driven lessons replace human-led discussions, students may miss the emotional and motivational support that human educators offer, such as empathy and guidance. Also, the reduction of face-to-face interactions and feedback sessions, replaced by automated feedback, might strip the learning process of its inherent human connection.

Challenges to Academic Integrity: The use of AI tools may complicate issues of plagiarism and academic misconduct. For instance, the ease with which students can use AI to generate detailed answers could blur the lines of independent research, making it difficult to determine if a student's work is their own. Also, there is the risk of students being wrongly accused of misconduct if they are unable to recreate the original AI-generated source of their information because of AI’s inherent variability.

Resource and Equity Issues: Implementing AI on a large scale can be resource-intensive, straining the budgets of educational institutions. Not all institutions may possess the infrastructure or technical expertise to implement, deploy, and maintain AI tools. This can widen the educational divide, with well-resourced institutions providing AI-enhanced education while others lag behind. This disparity may manifest between urban and rural areas, or between developed and developing nations. Additionally, there is the potential for job displacement in the education sector, as AI may reduce the demand for certain roles. There may be concerns about the associated costs of adopting AI technologies, as well.

In addition to the above, there are also concerns about:

• AI Bias: There is a potential for AI to reflect and amplify societal biases in educational content.

• Data Privacy: There are numerous issues surrounding the confidentiality and privacy of student data, as well as preventing potential misuse of this data.

• Homogenization of Thought: The over-reliance on AI tools can lead to a uniform way of thinking, curbing creativity and diverse perspectives in academic discussions.

• Technical Challenges: Implementation, updates, and maintenance of AI tools can be complex.

• Security Risks: There are increased cyber vulnerabilities associated with the implementation and use of AI software and systems.

• Reputation Risks: Over-reliance on AI may negatively affect institutional prestige and student recruitment.

• AI Overload: For some students and educators, the introduction of AI tools can be overwhelming.

• Over-commercialization: There are possibilities of corporate, commercial, and market interests overshadowing genuine educational needs.

These challenges must be addressed through careful planning, ethical guidelines, and the development of AI literacy among educators and students to ensure that the benefits of AI are realized without compromising the core values of education.

As can be seen from the summary above, the research into AI in education has identified a number of serious risks and challenges. If AI is to be integrated into the classroom, both educators and students must be fully aware of these risks and challenges and work collaboratively to address them. This is the topic of the fourth and final post of this introductory series.

News and Announcements

Interested in learning more about AI? 

Regis faculty are encouraged to self-enroll in the "Using AI in your Teaching" course created by Dr. Diana Perdue. Faculty can access the course here (don't forget to click the "enroll me" button).

Interested in contributing a post or joining our Regis College Artificial Intelligence Faculty Learning Community?

Contact Allen Karsina at allen.karsina@regiscollege.ed

---

References

The sources loaded into the notebook in NotebookLM at the time this post was written are included below.

Baker, R. S. & Hawn, (2020). Algorithmic Bias in Education. Retrieved from https://learninganalytics.upenn.edu/ryanbaker/AlgorithmicBiasInEducation_rsb3.7.pdf on December 25, 2024.

Bobula, M. (2024). Generative Artificial Intelligence (AI) in higher education: a comprehensive review of challenges, opportunities, and implications. Journal of Learning Development in Higher Education, 30, 1-27.

Chan, C. K. Y., & Colloton, T. (2024). Generative AI in higher education: The ChatGPT effect. Routledge.

Giarmoleo, F. V., Ferrero, I., Rocchi, M., & Pellegrini, M. M. (2024). What ethics can say on artificial intelligence: Insights from a systematic literature review. Business and Society Review, 129(2), 258–292. https://doi.org/10.1111/basr.12336

Jennings, A. M., & Cox, D. J. (2024). Starting the conversation around the ethical use of artificial intelligence in applied behavior analysis. Behavior Analysis in Practice, 17(1), 107–122. https://doi.org/10.1007/s40617-023-00868-z

Kim, S. L., Cheong, M., Srivastava, A., Yoo, Y., & Yun, S. (2020). Knowledge sharing and creative behavior: The interaction effects of knowledge sharing and regulatory focus on creative behavior. Human Performance, 34(1), 49–66. https://doi.org/10.1080/08959285.2020.1852240

Lee, S. S., & Moore, R. L. (2024). Harnessing Generative AI (GenAI) for Automated Feedback in Higher Education: A Systematic Review. Online Learning Journal, 28(3), 85-104. https://doi.org/10.24059/olj.v28i3.4593

Parasuraman, R., & Manzey, D. H. (2010). Complacency and bias in human use of automation: an attentional integration. Human Factors, 52(3), 381-410. DOI: 10.1177/0018720810376055

Resnik, D.B., Hosseini, M. The ethics of using artificial intelligence in scientific research: new guidance needed for a new tool. AI Ethics (2024). https://doi.org/10.1007/s43681-024-00493-8

Urmeneta, A., & Romero, M. (2024). Creative Applications of Artificial Intelligence in Education. Palgrave Macmillan.

West, D., Luzeckyj, A., Toohey, D., Vanderlelie, J., & Searle, B. (2020). Do academics and university administrators really know better? The ethics of positioning student perspectives in learning analytics. Australasian Journal of Educational Technology, 36(2), 60–70. https://doi.org/10.14742/ajet.4653

Yang, S. J. H. (2021). Guest Editorial: precision education - a new challenge for AI in education. Educational Technology & Society, 24(1), 105–108.

Acknowledgements 

ChatGPT 4o was used to suggest improvements for the text for some portions of this post.

This post was written by the author with the exception of the excerpts from NotebookLM.

The image was generated using Dall-e3 on ChatGPT by the first author.

The audio was generated using NotebookLM by uploading a draft of the blog and using the "audio overview" function.