AI and Research, Step 5: Reading and Note-Taking
In today’s episode, we’ll explore how AI can fit into the fifth step of the research process: Reading and Note-Taking.
Reading, Viewing, and Listening
- Have a preliminary outline available for reference.
- Scan the resource for a general overview, paying attention to:
- Headings
- Highlighted words
- Hyperlinks
- Chapter headings
- Organizational landmarks
- Read, listen, and view with purpose.
- AI may be used to:
- Provide focus:
- Sample prompt: “Review my preliminary outline and the attached resource. Identify main ideas that appear in the source and also align to the preliminary outline. List ideas to look for in a checklist format.”
- Enhance comprehension:
- Explain challenging passages.
- Define academic or technical vocabulary in context.
- Break down complicated sentences.
- Sample prompts: “I’m reading the following passage as part of my research. Explain the difficult ideas in simpler language but stay closely grounded in the original passage and don’t add new information.” “My guiding research question is: [insert question]. What should I pay particular attention to as I read this passage? Don’t answer the research question for me.”
- Provide focus:
Note-Taking
- A thinking process for students:
- “What matters?”
- “How does this relate to my research?”
- “What should I leave out?”
- “What deserves a direct quotation?”
- “What can I paraphrase?”
- “What larger idea does this support?”
- “What questions does this raise?”
- Choosing a tool:
- NoodleTools
- Google Docs:
- Tabs
- Headings
- Comments
- Microsoft OneNote:
- Notebook
- Section
- Pages
- Consistent format:
- Important to capture similar information for each note
- Example:
- Guiding question or theme
- Source
- Information
- Note type, such as statistic, fact, paraphrase, or quote
- Student thinking
- Types of content to capture:
- Direct quotations: exact language from the source
- Paraphrases: information restated in the student’s own words
- Summaries: condensed versions of larger sections or ideas
- Evidence: statistics, examples, facts, research findings, or other support
- Interpretation: what the student thinks the information means
- Questions and reflections: ideas the student wants to further investigate
Productive AI Use
- Potential problems may arise if AI:
- Generates notes from a source that the student hasn’t actually read.
- Summarizes inaccurately.
- Removes nuance.
- Decides what is important instead of requiring the student to decide.
- Blends source information with generated information.
- Produces paraphrases that remain too close to the source.
- Separates information from its original context.
- Makes it unclear which source an idea came from.
- After students have completed their initial reading and note-taking work, AI may be helpful as a support tool to:
- Identify ideas appearing across several sources.
- Suggest categories within a student’s notes.
- Identify areas where sources agree.
- Point out conflicting information.
- Identify notes that could reasonably fit under more than one guiding question.
- Help turn student-entered information into a source matrix.
- Sample prompts include:
- “Below are my notes from several sources: [attach notes]. My preliminary research outline is also included: [attach outline]. Suggest where my notes might fit within that outline. Identify notes that could fit in more than one section and information that doesn’t seem to fit anywhere. Do not add information or rewrite my notes.”
- “Attached is my outline with research notes included: [attach outline with notes]. Review the placement of my notes and point out areas where the organization might be improved or where notes may have been misplaced. Also point out where I might need more information. Do not reorganize the outline for me. Rather, provide observations and options as constructive feedback.”
- The overall process for this step might look like the following:
- Students open their preliminary research outline.
- They select a guiding question or information need.
- They read an appropriate source.
- They take their own notes.
- They connect each note to the relevant section or guiding question.
- They clearly distinguish quotations, paraphrases, evidence, and personal thinking.
- After gathering notes from multiple sources, they give their notes to AI.
- AI helps identify patterns, themes, overlaps, or possible organizational structures.
- Students decide whether those suggestions accurately represent what they learned.
- Students revise either their note organization or their preliminary outline as needed.
For more information about artificial intelligence, explore the following AVID Open Access article collection: AI in the K–12 Classroom.
#517 — AI and Research, Step 5: Reading and Note-Taking
AVID Open Access
15 min
Transcript
The following transcript was automatically generated from the podcast audio by generative artificial intelligence. Because of the automated nature of the process, this transcript may include unintended transcription and mechanical errors.
Paul Beckermann 0:01
Welcome to Tech Talk for Teachers. I’m your host, Paul Beckermann.
Transition Music with Rena’s Children 0:05
Check it out. Check it out. Check it out. Check it out. What’s in the toolkit? What is in the toolkit? What’s in the toolkit? Check it out.
Paul Beckermann 0:16
The topic of today’s episode is “AI and Research, Step 5: Reading and Note-Taking.” This is part five of a seven-part series exploring the possible integration of AI into the research process. So far, we’ve progressed through the first four stages in our research process: task definition, planning and gathering background knowledge, searching for sources, and evaluating the information that has been found.
Now that we’ve gathered what we believe to be relevant, credible, high-quality, and complete information to support our research goals, it’s time to dig into them more deeply and learn what they have to offer us. This is a key stage because students are transitioning from finding information to processing it and making meaning from it—this is where students do much of their learning. Specifically, students will be reading, viewing, or listening to the content, taking notes, and organizing those notes in alignment with their preliminary plan.
Let’s start with reading, viewing, and listening. Research is no longer simply text-based. So, while students will almost certainly be reading some of the content they found, they may also be viewing and listening. As students begin this part of the process, they should have their preliminary outline close at hand, and they should use it to guide their work. This document is their research plan, and while it can change as they go, it’s an important tool for giving them focus. So have that nearby. While students have done an initial analysis of each source for relevance, they may find, as they dig deeper, that they missed the mark a little bit and should discard a source or maybe move on to the next source on their list. That’s okay, and it can save them a lot of time from reviewing unrelated content.
To help with this part of the process, students can skim the source, paying attention to headings, highlighted words, hyperlinks, chapter headings, and other organizational landmarks like these. Based on this scanning of the content, they can identify topics from their preliminary outline to focus on as they dive in more deeply. This allows students to read, view, and listen with specific purpose, rather than highlighting everything that seems interesting.
Students read, view, and listen with particular information needs in mind. For example, students might enter a source looking for evidence related to one guiding question, an explanation of a particular concept, statistics or examples, a perspective that they hadn’t encountered, or maybe evidence that supports or complicates their preliminary thinking. While students should have a defined goal in mind, it’s also important to remain open to unexpected information. Plans may change as students learn more.
AI can be helpful here if you choose to allow it for your students. Students can input their preliminary outline and a source into an AI chatbot or maybe a tool like Gemini Notebook. They can use a prompt such as: “Review my preliminary outline and the attached resource. Identify main ideas that appear in the source and also align to the preliminary outline. List ideas to look for in a checklist format.” This type of preview can help students focus their reading, listening, and viewing process. This generally works for video and audio files as well as text-based resources, but you’ll want to check with your chosen chatbot to see what types of files it will accept.
Another way that AI can be helpful is by supporting comprehension. Before students can take meaningful notes, they must understand what they’re reading, hearing, or viewing. If a student is struggling with reading comprehension, AI can scaffold difficult text by helping students explain challenging passages, define academic or technical vocabulary in context, or break down complicated sentences.
For example, a student might prompt the AI tool this way: “I’m reading the following passage as part of my research. Explain the difficult ideas in simpler language, but stay closely grounded in the original passage and don’t add new information.” Or they might prompt: “My guiding research question is: [insert question]. What should I pay particular attention to as I read this passage? Don’t answer the research question for me.” Similar prompts can be used for other types of media as well.
Next, let’s move on to note-taking. As students read, view, and listen, they are not merely transferring information from one source to another. They should be determining if the ideas and information presented are worth recording as notes, and if they are, what information should be captured. Content should go from one source through the student’s brain, and then find its way onto a note that might be used later in the research process. In other words, note-taking is a decision-making process.
As students process the information in their sources, they should be asking questions such as: “What matters? How does this relate to my research? What should I leave out? What deserves a direct quotation? What can I paraphrase? What larger idea does this support, or what questions does this raise?” Those decisions are part of learning. This is one reason having AI simply “take notes on this article for me” is problematic. It removes much of the thinking that note-taking is intended to develop.
Traditionally, the note-taking process involved using index cards to categorize and record notes. That approach is still a valid process for your students to use. However, if you wish to move the process to a digital environment that enables easier and more efficient searching, editing, and rearranging, there are digital options to consider.
One option is to purchase a product like NoodleTools, which is specifically designed for this task. Students create virtual note cards and tag them to the sources they’ve been taken from. Notes are identified as quotations and paraphrases right on the card, and this helps students explicitly identify how they’re capturing ideas. While this is a great option, it also costs money and may not be an option for everyone. If you don’t have a budget for this, you can consider tools that you already have access to.
For instance, Google schools might make use of a Google Doc. Taking advantage of the tabs and headings features, students could create one tab for each major part of the preliminary outline, and then sub-tabs for individual questions or themes. For example, students might create a tab labeled “Effects of Social Media” with sub-tabs like “Mental Health,” “Sleep,” and “Academic Performance.” It becomes like a mini-outline within the document.
Within each section, students could record the source, page, paragraph, or location of the information, a quotation or paraphrase, key information, and also their own thinking about what they’ve learned. The comments feature could also be used for questions or personal reflections, keeping those thoughts visually separated from the source notes. In Google Docs, you simply highlight part of the text and then click on the comments button. Your comments appear in the margin.
This can be a good choice because if students already know how to use a Google Doc, it lowers the overall learning curve and saves more time for the research. Tabs can also be moved around, edited, and searched. A potential limitation of this approach might be that if students don’t use a consistent structure, notes can become one long document, and that can become unmanageable. You’ll want to have your students watch out for that.
For schools using Microsoft 365, OneNote is particularly well-suited to this work because students can organize research using notebooks, sections, pages, and tags. Microsoft describes sections and pages as the basic organizational structure, and individual notes can be tagged for classification or follow-up. A research notebook might be: Notebook: Research Project; Section: Guiding Question 1; and Pages for Source A, Source B, Source C. Each classroom is unique, so you’ll want to find an option that best fits your needs and circumstances.
And of course, the information captured and recorded is more important than the tool or application that you’re using. Whatever tool students use, it’s important that they record roughly the same information with each note. For instance, each note might have a consistent format that includes: guiding question or theme, source, information and note type (statistic, fact, paraphrase, quote, things like that), and then the student’s thinking.
Students will need guidance as to what types of information to record. They’ll need to be able to distinguish among the available options, know how to effectively capture each option, and identify when to use each one. Choices might include:
- Direct quotations (exact language from a source)
- Paraphrases (information restated in the student’s own words)
- Summaries (condensed versions of larger sections or ideas)
- Evidence (statistics, examples, facts, research findings, and other support)
- Interpretations (what the student thinks the information means)
- Questions and reflections (ideas the student wants to investigate further)
One particularly important habit is to keep source information and student thinking visually distinct. In other words, they might have the evidence, quotes, and paraphrases in one area of each note, and their personal interpretations of that information in another place. Again, they may use the comment feature for their own reflections, keeping them on the edge. However they do it, they should guard against misinterpreting their thoughts and wonderings as factual research.
Students also need to retain enough citation information to know exactly where each note came from. If they can’t trace the information back to a source, they won’t be able to use it in their work.
Throughout this note-taking phase, students will need to use AI carefully and thoughtfully. If used poorly, AI can create several shortcuts that will undermine this stage of the process. More specifically, AI could cause problems by:
- Generating notes from a source that the student hasn’t actually read
- Summarizing inaccurately
- Removing nuance
- Deciding what is important instead of requiring a student to decide
- Blending source information with generated information
- Producing paraphrases that remain too close to the source
- Separating information from its original context
- Making it unclear which source an idea came from
Productive use of AI would be something like, “I don’t understand this section, help me unpack it,” while unproductive use would be, “Read this article and give me the notes I’ll need for my paper.” The first option scaffolds reading; the second one potentially eliminates it completely.
The best option for AI use is to have the students do the initial reading and note-taking without AI. Once that has been completed, then AI can be used productively. For instance, after doing their initial note-taking work, students might ask AI to:
- Identify gaps appearing across several sources
- Suggest categories within their notes
- Identify ideas where sources agree
- Point out conflicting information
- Identify notes that could reasonably fit under more than one guiding question
- Help turn student-entered information into a source matrix
Here’s a sample prompt that might be used: “Below are my notes from several sources. My preliminary research outline is also included. Suggest where my notes fit within that outline. Identify notes that could fit in more than one section and information that doesn’t seem to fit anywhere. Do not add information, rewrite my notes, or draw conclusions for me.”
Notes, preliminary outlines, and prompts can be inputted into any generative AI chatbot, but Google’s Gemini Notebook might be the best option for this, since all the sources and notes can live within the same notebook and be queried in any combination or configuration. This offers a lot of flexibility and makes the process very accessible.
For step five in the research process, a good overall mantra is “Student first, AI second.” The process for this step might look like this:
- Students open their preliminary research outline.
- They select a guiding question or information need.
- They read an appropriate source.
- They take their own notes.
- They connect each note to the relevant section or guiding question.
- They clearly distinguish quotations, paraphrases, evidence, and personal thinking.
- After gathering notes from multiple sources, they give their notes to AI.
- AI helps identify patterns, themes, overlaps, or possible organizational structures.
- Students decide whether those suggestions accurately represent what they learned.
- Students revise their note organization or their preliminary outline as needed.
In this scenario, AI is providing feedback or acting as a thinking partner. The students remain in the lead learner role. That’s the key. In step five, students are learning. They’re processing through the content they’ve gathered and figuring out what it all means in the context of their research question or topic. There will definitely be productive struggle, and that’s a good thing. AI can be a helpful thought partner, but we need to make sure that AI doesn’t do too much and remove that struggle.
To learn more about today’s topic and explore other free resources, visit avidopenaccess.org. Specifically, I encourage you to check out the article collection, “AI in the K-12 Classroom,” and of course, be sure to join us next Wednesday for our full-length podcast, Unpacking Education, where we’re joined by exceptional guests and explore education topics that are important to you. Thanks for listening. Take care, and thanks for all you do. You make a difference.