AI writing is here – teachers be aware

I intend this post as a public service announcement of a sort for educators at all levels. If you have not personally explored AI assisted writing, you need to do so. I will explain how. I say this because your students will soon explore AI services that will generate written products for them and you will have to adjust how you think about writing assignments as a consequence.

My suggestion is that you give a service called ChatGPT a try. Sign up and get a free account. The service is very easy to use. Once you have an account, you simply enter a description of what you want into a text box and wait for a reply. I think the sophistication of what is generated is likely to shock most and this reaction should cause you to consider what access to a service like this means for the tasks you describe in your classroom.

Here are a couple of examples. These examples relate to topics I might raise in a graduate educational technology course. My point is these are challenges I might offer students first to see if they understood a topic we had covered and then if they could connect this topic to other cognitive phenomena.

Me: What is a semantic network?

ChatGPT: A semantic network is a graph-based representation of a knowledge domain. It is a way of representing structured knowledge by modeling the relationships between concepts. In a semantic network, concepts are represented as nodes in the graph, and the relationships between concepts are represented as edges that connect the nodes. This allows for the representation of complex ideas and their relationships in a clear and intuitive manner. For example, a semantic network could be used to represent the relationships between different types of animals, their characteristics, and the ways in which they interact with each other.

Me: How can a semantic network explain the tip of the tongue phenomenon?

ChatGPT: The tip of the tongue phenomenon, also known as “TOT,” is a common experience in which a person knows that they know a word or a piece of information, but they cannot recall it at the moment. One possible explanation for this phenomenon is that the information is present in the person’s semantic network, but it is not easily accessible at the moment. In a semantic network, information is typically represented as nodes in the graph, and the connections between these nodes encode the relationships between different pieces of information. When a person experiences the tip of the tongue phenomenon, it may be because the information they are trying to recall is present in the network, but the path to access it is not easily accessible. In other words, the person knows that the information is there, but they cannot retrieve it easily because the connections between the relevant nodes in the network are not strong enough.

Me: Can the semantic network explain the testing effect?

ChatGPT: Yes, the semantic network can help explain the testing effect, which is the phenomenon whereby taking a test on material improves subsequent recall of that material compared to simply studying the material. The testing effect is thought to occur because taking a test forces a person to retrieve information from their memory, which strengthens the connections between the relevant nodes in their semantic network. This makes it easier to access the information in the future.

——–

Just so you appreciate what you are reading try this. Take the final question “Me: Can the semantic network explain the testing effect?” and enter it as a Google search. You will generate plenty of hits, but the hits are not really answers to the question. The hits at the top of the list I received were explanations of what a semantic network is and represented content I would have to read to generate an understanding. I did find an explanation of what the testing effect is in another hit further down the list. I did not find a resource near the top of the list that would cover a possible connection between the two. Educators may be familiar with the testing effect, but why it works so successfully is fairly speculative. I explain it by connecting the concepts of a networked associative model of memory and the cognitive mechanisms of the retrieval process which is kind of what I would be looking for if I had asked the question of students who have discussed these concepts with me. I was impressed AI put it together in a similar way.

So, AI writing is not simply retrieving what someone else has written (search), but is building from a huge collection of content at a more abstract level.

So? Well, students can “write” impressive products by giving an AI bot instructions. They may do this because they want to read how the AI bot generates a response they would find informative (Note: Search may soon be replaced by this type of AI process because it answers questions rather than just providing resources you can use to answer them yourself). AI can be your teacher.

However, if you are teacher using writing to evaluate learning or writing skill or if you are a teacher using writing as a way to encourage student learning (writing across the curriculum), the “writing” generated by AI is a challenge for you. It does not require much from the student in terms of content review, application of writing skills, or personal understanding. Like math teachers who figured out students could take a picture of a problem the students were assigned and have an online service solve it and show a solution process, you are now dealing with a new reality. Writing extended content is also a process that is much more difficult to monitor. You can watch students write a theme in class, but a research paper is a different beast.

Let’s start with this. Take some time to explore ChatGPT. You really need this personal experience to understand present capabilities. Don’t start by thinking how you might ban access. This will not be realistic AND it ignores the positive opportunities this type of tool offers. Are there opportunities you can think of? Now, what about limitations? What about citations? This service strikes me as a very intelligent colleague who can spout off on nearly any topic, but leaves me with little I can read and consider myself. How could I as a writer even use content a service like this might generate in something I would write? How would I justify the statements made? My first reaction is that educators review what they know about the Flower and Hayes writing process and consider what tangibles they might ask students provide at each stage of the process. For example, what are the notes they generated from the sources they intend to cite in their final product. How did they put these notes together in getting to this final product?

One more thing. I wrote a previous post about ChatGPT for Medium and in this post I included the response to a question about how AI writing might limit what students learn from writing themselves I asked of ChatGPT. I thought the response was quite useful and honest (now I am anthropomorphizing). Honesty is not always something you get with human authors.

Loading