I have adapted lessons to follow on from one that I found on the Digital Learning Hub.

AI Emotions

Year level 5-6

Summary

Using Natural Language Processing in the real world.

Studying poetry and needed to identify tone and mood. Could AI accurately tell us this?

Suggested steps

Lesson 1:

Follow this unplugged activity from digitaltechnologieshub.edu.au:

This task explores systems that use NLP to classify a reviewer’s online text as positive, neutral or negative, based on words that might appear in the text. This is often referred to as ‘sentiment analysis’.

1. Provide a range of online reviews for students to view and decide if they are positive, neutral or negative. What words provide students with that overall impression?
2. Provide students with the worksheet, Positive, neutral or negative.
   • Task 1 asks the students to classify words as positive, neutral or negative.
   • Task 2 asks students to write and share a review, with their partner working out if the overall impression of the review is positive, neutral or negative.

Lesson 2:

Follow this plugged lesson from digitaltechnologieshub.edu.au: Code your own sentiment analysis program

In this task, students code their own program using a visual programming language such as Scratch to demonstrate sentiment analysis. The program identifies a word contained in the user’s input (string). If that word is recognised then a particular response is given else provide a generic response. The program incorporates:

• user input, using an ask block
• branching, using if/then/else blocks
• iteration, using a forever block.

Lesson 3:

1. Present students with the challenge of creating a program that classifies a user’s review of something as positive, neutral or negative.
2. Discuss possible ways to program a response based on the user’s input text.

Follow up with this English focussed lesson:

1. Provide a range of poems for students to view and decide if they are positive, negative or neutral in tone.
2. Students identify the words that give this overall impression.
3. Adjust the AI program created in Lesson 2 and run it using the poems.

Discussion

• When training an AI, words and combinations of words would be classified as positive, neutral or negative through the process of supervised learning. Supervised learning is the process of the human providing the program with lots of examples of what it is we are wanting it to identify along with a label.
• Why is it more complex when looking at poetry, then just looking at reviews?

Why is this relevant?

As a result of doing this task student’s understanding of how AI can be developed to help solve a problem. This topic is directly related to the English unit, but the wider implications are for learning about social media etc, who collect information using a similar form of AI training.

In relation to Digital Technologies:

• text recognition
• text classification.

Algorithms and programming are essential to developing machines powered by AI.

In conventional programming, the computer is provided with a set of instructions for a defined set of scenarios. In this lesson, students hardcode a program that is based on identifying a word contained in the user’s input (string). If that word is recognised, then a particular response is given. Else provides a generic response.

The downside with this programming is that every possible option needs to be hardcoded to ensure the text is correctly categorised. Also, the order that the word appears in the text affects the categorising. In an AI, a similar problem arises. We need to teach the AI each individual word, however the AI is good at solving all sorts of word combinations.

Curriculum links

Links with the Digital Technologies curriculum area

ADD Links with other curriculum areas