Monday, December 18, 2023

Ai perceptions among educations

The Method:

We copied the last 30 threads from nine largest Fb groups on AI and education. The document, over 1000 pages long (142558 words) was uploaded to ChatGPT, with a request to perform sentiment analysis. The groups are:

  • ChatGPT for Teachers & Educators
  • AI For Teachers
  • ChatGPT for Educators
  • AI for Teachers
  • The AI Classroom
  • ChatGPT for Teachers
  • Higher Ed discussions of AI writing
  • AI Teacher Resources with ChatGPT, Canva, & Midjourney
  • Higher Ed Learning Collective
  • AI and ChatGPT in Education

The results are below:

“Here’s a summary of the key sentiments expressed:

  1. Privacy and Data Security Concerns: Educators express concerns about privacy issues related to grading student work using AI tools like ChatGPT, citing issues such as data anonymization and the potential for data breaches. Some educators acknowledge the measures taken to anonymize data, while others suggest looking into AI companies that handle security well.
  2. Regulatory Compliance: Awareness of regional differences in data privacy regulations, such as GDPR in Europe, influences educator attitudes towards AI in education. Some educators express understanding of why companies are concerned about data privacy compliance, while others are less worried personally.
  3. Potential Risks and Misuse: There is a discussion about the potential risks associated with AI, including the re-surfacing of data and the reliability of AI outputs. Concerns are raised about AI’s potential to propagate misinformation and its impact on the educational process.
  4. Practical Applications and Benefits: Educators discuss practical uses of AI, such as assisting in grading and providing feedback, and generating teaching materials and lesson plans. AI is seen as a tool that can save time and enhance the learning experience.
  5. AI for Personalized Education: AI is considered useful for tasks like writing recommendation letters and creating personalized reports, highlighting its potential in catering to individual needs.
  6. Enhancing Creativity and Engagement: Some educators are exploring innovative ways to use AI for creative projects and enhancing student engagement, such as creating chatbots for educational purposes and using AI for art creation.
  7. Concerns About Ethical Implications and Academic Integrity: There are discussions about ethical considerations, such as the impact of AI on cheating and academic integrity. Educators ponder how AI might affect the nature of assessment and student work.
  8. Need for Professional Development and Policy Frameworks: The importance of professional development for educators to understand and effectively use AI is emphasized. There are requests for AI use policy templates and guidance on integrating AI into educational practices.
  9. Diverse Perspectives and Experiences: The sentiment among educators varies widely, with some expressing excitement and optimism about AI’s potential in education, while others show caution and skepticism. This diversity highlights the need for continued dialogue and exploration of AI’s role in education.
  10. Emerging Tools and Platforms: Educators are actively exploring and sharing various AI tools and platforms that can aid in teaching and learning, demonstrating a keen interest in staying abreast of technological advancements.

In summary, while there is significant interest and optimism about the potential of AI in education, concerns about privacy, data security, and ethical implications are prominent. The educators also highlight the importance of professional development in AI, the need for policies to guide its use, and the exploration of creative and innovative applications to enhance teaching and learning.” (ChatGPT 4, retrieved 12/14/2023).


Comment: The sample includes only educators and others already interested in the uses of AI in education, with one exception. They are in no way a representative sample. However, even among this self-selected groups, the concerns still dominate over excitement and over pragmatics. While concerned, educators readily exchange practical tips on how to use AI to reduce their own workload. They are also very curious about specialized AI tools developed for educators. This should be taken into consideration by anyone panning to develop policy or offer professional development to educators.

Disclaimer: This analysis is done within the legal framework of investigative reporting, which does not require a formal IRB approval. Although I am a trained researcher, I am acting here as a blogger/journalist. This is not research and does not imply any claims of validity.

Thanks to Adriana Menjivar Enriquez for assistance. Feel free to suggest other questions to ask about the file. I have several in mind, and will publish more results next week.

Do AI bots deceive?

The paper, Frontier Models are Capable of In-Context Scheming , arrives at a time when fears about AI’s potential for deception are increasi...