Intelligent AI Agents Helping Children Learn

I am excited about the potential for good that Artificial Intelligence (AI) has in the education system. Every child is unique, with different interests, natural abilities and preferred ways of learning. AI can be used to personalise learning for each child, providing them with the content and instruction that they need to succeed.

My daughter is an avid reader. She reads a dozen or more books each week. The school she attends has a star reader program, were children earn points by reading books and writing short reviews. This program encourages children to read and also develops valuable skills such as reading comprehension and summarisation.

I wondered if there was a way to use conversational AI based on large language models (LLMs) to summarise all the reviews of a particular book and get more children interested in reading. LLMs are powerful AI models that can be used to generate text, translate languages and answer questions. They can also be used to summarise text, which is what I wanted to do with the reviews of the books.

I found that it was quite easy to use a conversational AI to summarise the reviews of a book. I first created some dummy review data, which I just used to validate the workflow.

Creating Dummy Review Data

I then asked the conversational AI to summarise the reviews and answer questions such as "which character and scene do readers like the most?"

Book Reviews Summary Insights

The conversational AI had no problem in distilling this information.

I then asked another conversational AI, one that specialises in converting text to an image, to visualise the favourite scene, "The peach landing in New York city".

The Peach Lands in New York

The combination of the scenes of the peach landing on a skyscraper and later being moved to Central Park is impressive.

This approach can be used to highlight or showcase a popular book and encourage children to read it. If we then notice an increase in the number of children lending the book, we might be able to attribute this to it being showcased.

Additionally, conversational AI based on LLMs can be used to generate personalised recommendations for books. This can help children to find books that they are likely to enjoy, which can further encourage them to read.