Anti-bullying AI

We are always on the lookout for engaging scenarios that teachers and students would appreciate. This one here is a result of a collaboration with our good friends from the Digital Technologies Hub and Apps for Good in the UK.

Sometimes we write and post things on social media in a hurry. Such posts can hurt people, and they feel bullied. Wouldn't it be great if an AI could check our posts as we write them and warn us if they are potentially hurtful?

AI is an excellent candidate for this kind of scenario, as there are so many different ways of combining words into full or partial sentences that are difficult to hardcode with if-then-else statement (branching).

Training data

It won't be too hard for students to come up with a couple of nice and mean things to say and enter them into a table. This will be our training data.

Not sure what to write? Here are a few examples to get you started.

While students type in their training data. The AI gets configured. We felt strongly that this was important to show since the connection between data and the AI is often a bit of a mystery.

When we have entered all the training data, our network looks like the one below. A beautiful 3-layered artificial neural network with one input perceptron for each unique word, 10 perceptrons in the hidden layer and two perceptrons that will tell us whether the word (or words) are kind or mean.

While we see words, the AI sees numbers, slimeball in the image above is represented as a '1', as we can see when we hover over the perceptron in the input layer that is connected to the input word.

Yes, we see binary numbers at work here. We could as well have used decimals, but there was no need. We'll talk about them in a future post.

Let's quickly run the training process by clicking on the start learning button in the top right corner of our screen and then drag the little slider to the right to speed up the process.

The training data will be shown to the AI and it will make a series of repeated improvement attempts until the error of the network falls below a preset threshold. The dial at the bottom-right will eventually turn green when the training process is complete. Voila.

Let's now enter a post for the AI to analyse. We could try you smell so nice. Note how the AI initially considers you smell so as 'mean' until the word nice tips the verdict in favour of 'kind'. Note that this particular example was not part of the training data.

The AI is actually 78% certain that the meaning of the sentence is nice, which we can see when you hover the mouse over the ''Kind things output perceptron.

Btw, these little popup windows are available for every perceptron and allow your students to trace the flow of data throughout the entire network.

Have a go and type in a number of different posts and observe what the AI thinks about them. Remember, it has only seen 12 examples of posts, so its experience is a bit limited. It will especially struggle with irony and sarcasm and of course with any words it doesn't know. But we can see how it will get better and more rounded with bigger datasets and perhaps with a thesaurus to find out about similar words. But overall, not a bad result for 5 minutes of work and zero lines of coding.

If you want to try this yourself? Head over here: You will need to create a free teacher account, which takes no more than 30 seconds. Student accounts can be purchased from the built-in shop for a reasonable amount of $5.

Let us know what you think.

Until next time,

The Doctor.

Acknowledgements. We'd like to thank Apps For Good, UK and the Digital Technologies Hub for their contributions to the inspiration and refinement of this scenario.

Update [17.10.2019]: The lesson plan for this activity, jointly developed by the Digital Technologies Hub and the Digital Technologies Institute, is now available. It can be accessed on the DT Hub Website.

More free stuff for teachers.

The B4 Computing Kit now has a virtual companion where you can run a range of computing experiments in a simulator. On mycomputerbrain.net you find a great number of experiments suitable for primary and secondary students. Explore binary numbers, computer graphics, arithmetics and even artificial intelligence. Most of them do not require any coding. How cool is that?

This is the start page with access to the four topic areas.

You might want to explore how the computer works.

Here is one of the experiments.

How about Computer Graphics?

Or maybe Artificial Intelligence?

The platform is free for teachers. Student licenses start at $3. Let us know what you think and what else you would like to see on the platform. Needless to say, the online experiments are even better when accompanied with the physical B4 kits, which you can order here.

Yes, we can (understand a computer deeply)

Many students leave secondary school after completing computing courses of various flavours but would display a mystified look if asked to explain how a computer actually works. Having participated in deliberations for various draft computing syllabus discussions over the years, I am astonished at how little emphasis or interest this receives from teachers of computing and curriculum designers. Perhaps this is because they themselves have never truly understood the processes involved.

A deep-seated human desire to understand

Yet when I conduct lessons with students, explaining the various components of the CPU and the way in which they work together, explain logic gates, build and test corresponding logic circuits and ensure they truly understand binary numbers, I discover they are deeply appreciative of the effort and express surprise that it wasn’t explained to them before. There is a deep-seated and very human desire in each of us to understand. Students seem to acquire a conviction that computers are so complex, it is pointless to attempt to really understand any of this. The extent of their understanding appears to be that computers use binary code which they hold in millions of tiny transistor gates and manipulate to produce output. That’s as far as it goes.

A paper computer by IBM

The first time I addressed this issue in my teaching was back in 1994 when I constructed a ‘paper computer’ using a backboard and a paper flap which pushed through slots to indicate how the various registers filled and manipulated data and addresses. I was inspired by a kit IBM once offered through the press and which I had long since lost - even IBM media enquiries in the US could not locate any sign of it. I scripted a ‘machine cycle drama’ to accompany it, where students filled various roles and read to the class the action being performed at each step of adding two integers 2 and 3 together.

David Ecks' book

Later I encountered a most wondrous book by David Ecks “The Most Complex Machine” (recommended!) with accompanying programs called xTuring, xLogic, xSort, xSearch and most wonderfully xComputer. This latter had its own assembly language and a GUI which bringing it all to life. It was now possible for me to simulate the reality of the cycle step by step on a computer screen. For years I could not understand why more attention had not been given to the machine cycle/ fetch execute cycle and why no one seemed to have invested in creating a genuine simulator to allow students to explore and appreciate it all.

Meeting the B4 Computer Processor

Quite by accident this year I came across Karsten Schulz's B4 and immediately ordered one. Here was the interactive modular CPU exploratory tool I wish I had years ago! Although extremely versatile and accompanied by a manual with many different explorations, I embraced my regular "go-to” for my students, to illustrate the way each component of a CPU works together in the simple addition of two integers. I was excited enough to take it along when I recently delivered a workshop of ideas for teachers at the 2018 ACCE Conference in Sydney. My delight when we I met its inventor at this Conference was matched by his delight as we shared our mutual conviction that computing students really do want to understand how computers work…and not just in a half-baked way. Really understand!

About the author:

David Grover has been Head Teacher of Computing at Chatswood High School, New South Wales and is the author of a number of texts and resources in secondary computing.