Through the act of reading, we gain meaning, understanding, and knowledge. We also make connections between texts, ourselves, and the world. Reading is an activity that will continue to shape us throughout our lives—in school, on the job, and in our daily lives as members of a literate society.
While reading might not be the first skill that people think of when they talk about generative AI tools—like ChatGPT, Google’s Gemini (formerly Google Bard), Claude, or Microsoft Copilot—the reading process can be enhanced by these new tools.
This impact may look different depending on the age of the learner. For younger students who are not yet allowed to use these tools, the teacher can model and lead the full class or a small group of students through the experiences, soliciting questions and ideas from them, and entering those ideas into the AI tool. In this way, students can participate by providing input, observing responses, and engaging in discussion about those results. They can even prompt the follow-up questions being asked; they just won’t be the ones actually doing the typing.
If you are teaching older students who can use these tools, you might still consider modeling at first, but students can eventually engage with the AI themselves. Whatever your situation, there are effective ways to leverage AI throughout the reading process.
Generative AI can be used during the pre-reading phase of the reading process to prepare students and set them up for a successful reading experience. To make the AI interaction most beneficial, the student or teacher should have access to a digital version of the text to be read. This provides the opportunity to copy and paste the text into the AI program, which allows the tool to know specifically what is being referenced and discussed. If it is a famous piece of writing, like Martin Luther King Jr.’s “I Have a Dream” speech or a play by William Shakespeare, the AI will likely be able to gather quite a bit of context from its databases, but for less well-known texts, it will be important to be able to feed it into the AI.
For example, students may be getting ready to read the short story The Lottery by Shirley Jackson. One way you could use AI in the pre-reading stage would be to gain some historical context for the story. That type of context will often help the reader better understand the setting, actions, and dialogue in the story. When the question “What historical context should I be aware of before reading The Lottery?” was entered into ChatGPT, the AI returned a list of seven helpful contextual points of which a student would likely not yet be aware. Some of these included a description of the time period the story was written, the political and cultural climate at the time, and a brief note about the controversy that surrounded the story when it was released. These points can help pique a student’s curiosity and set them up for a better understanding of what they are going to read.
Another pre-reading strategy is to have the AI help identify key vocabulary that might be challenging yet critical to understanding the text. For The Lottery example, you could paste in the text of the story and then ask a question, such as, “What are some key vocabulary words from this excerpt of Shirley Jackson’s story that a reader must understand?” In response to this particular prompt, ChatGPT returned a list of 11 terms that were key to the text and brief definitions of the terms in the context of the story. If you didn’t want your students to be given the definitions, you could instruct the AI to simply provide the terms without definitions. For The Lottery, the list included relevant words like “civic” and “tradition,” which are central to the story’s theme.
One more pre-reading strategy that you could use, especially with nonfiction texts, is to paste in the text from the article or document and then ask ChatGPT, or your generative AI tool of choice, to provide a brief summary. You could even tell it to limit the summary to three sentences to ensure that it’s kept short. This initial summary can provide students with a valuable overview and preview of the content. This can set the reader up for success and help improve comprehension. This approach is a little bit like scanning an article ahead of time to get the general idea of what is to come, which can be especially helpful if the text is complex or technical. If you’re reading as part of the research process, it can even inform whether or not you should take the time to read the article. The brief summary might quickly let you know if it’s even relevant to your larger research.
During the actual reading of the text, readers can also use generative AI as a reading partner. This might take a little practice, complete with trial and error, in order to get the most beneficial results. However, it can be a rich experience once you get comfortable with it.
One basic way to use AI to coach a reader through the reading process is to ask for a list of questions related to the content of the text. While it can be especially powerful to have students generate their own questions, there is a place for having the AI assist with this as well, especially as a scaffold for students who are struggling in this area or as a way to save time. If you do have students generate their own questions, you might have them paste in their list of questions and then ask the AI to identify additional key questions that they may have missed. To do this, have your students start by pasting in their own questions and then have them add the following at the end of the prompt: “These are the questions I have about this text. What am I missing? What else should I be asking in order to better understand this text?” This process allows the students to generate their own questions first and then prompts the AI to provide feedback on their work.
Students could even ask the AI to evaluate the quality of the questions they submitted and perhaps identify the best ones. Students could then discuss if they agree with the AI’s opinion. In a similar fashion, students could submit their thoughts on some aspect of the text and ask the AI for feedback. For instance, they might submit their understanding of the main point being made in the text and then ask the AI, “Do you agree with me? Why or why not? What are my blind spots?”
Another strategy is to offer the AI your own thoughts or interpretations about the text and then direct the AI to ask you a follow-up question to continue the conversation and probe deeper into the meaning of the text. In this way, the AI is not doing all the work for you. Instead, it’s helping you think more deeply in processing the text.
This type of conversation about The Lottery with ChatGPT went like this. A student entered:
“I wonder if the students in the story know why they are even gathering stones. Since children are often berated for throwing stones, it might feel ominous that they are gathering them. What do you think? Please ask me a follow-up question to keep the conversation going.”
As a response, ChatGPT returned:
“That’s an insightful observation about the children gathering stones in The Lottery. It indeed presents an ominous undercurrent, especially given the normal rules of behavior for children. Considering this, how do you interpret the adults’ reaction (or lack thereof) to this activity? Does their response, or absence of one, give you any clues about the nature of the lottery and the community’s attitude towards this tradition?”
This type of back-and-forth engagement with the AI can lead to some valuable, deep thinking and processing. It’s essentially like having a conversation about the literature with a thought partner—in this case, the AI chatbot.
Once a student has reached the end of the text, some of the same strategies that were used during the reading can be applied again. They could ask the AI for a list of probing questions to help them consider the deeper meaning of the text. Then, one at a time, they could submit a response to one of the questions and either ask the AI to pose a follow-up question or identify potential gaps and flaws in their logic.
For some students, it may be safer to begin having this type of conversation with a computer algorithm than a peer, as a computer might feel less judgmental or personal. Of course, it’s still crucial that students graduate to peer-to-peer interactions at some point. Still, AI can be used as a scaffold.
Another strategy that can be very engaging is to prompt the AI to have a debate with you about a key point or controversial issue in the text. To do this, it’s important to tell the AI that you wish to engage in a friendly debate about the text. You should tell the AI which position it will take, what your position is, and then instruct it to end each response by asking a follow-up question to help continue the conversation.
Students can engage in a similar give-and-take process with educational AI platforms, like Khanmigo, which use generative AI to allow students to have virtual conversations with authors and historical figures. This can be a fun way for students to internalize the content they’ve read and take it to the next level.
For readers who struggle with decoding words, text-to-speech tools, like Speechify, can unlock the text for students and allow them to access the content. Not only can this help them in school, but it can be an important life skill for struggling readers.
Generative AI can often translate content quite well into a student’s primary language. If the content and not the act of reading in English is the goal, this strategy can help students get to the content and not be left behind in the learning process.
Finally, AI can rewrite text at different reading levels. It’s common to see adults take a complex piece of text and ask AI to explain it to them as if they were a fifth grader. This also works well for students and is one way to make sure that they all have access to the academic concepts in the text. This foundation of knowledge will help them actively engage in the learning and the conversations about that content.
AVID Connections
This resource connects with the following components of the AVID College and Career Readiness Framework:
- Instruction
- Rigorous Academic Preparedness
- Student Agency
Extend Your Learning
- Schools Are Using Voice Technology to Teach Reading. Is It Helping? (Olina Banerji via EdSurge)
- AI Reading Assistance: A Revolutionary Tool or a Threat to Close Reading Skills? (Marc Watkins via Rhetorica)