Category: AI & Education

I found the Writing Process Model (Flower & Hayes, 1981; Hayes, 2012) helps me think about the development of writing skills and the specific application typically described as writing to learn. This model identifies the processes and the interaction among the processes involved in writing and has been used to guide both writing researchers and the development of instructional tactics. 

The model provides researchers and instructional designers with a concrete framework to work with by identifying specific skills that can be studied as the source of individual differences in writing skills or targeted for development, assuming that greater proficiency with these skills will lead to more effective writing.

I first used this model to speculate how specific technology tools could support writers. For example, technology offers powerful ways to take and review notes, a method for planning by creating an outline or “mind map”, and a way to record text that allows for easy manipulation and revision. I have begun to think about the model in a different way brought on by easy access to AI for writing in general and in classrooms more specifically. Given the general goals of learning to write and writing to learn, when do specific uses of AI facilitate and when do these applications harm the development of the writing subprocesses as involved in each category of writing experience? Put another way, instead of thinking of AI as an all-or-nothing approach to creating written content, would it make more sense to evaluate the use of AI in impacting writing subprocesses and perhaps have students use AI more selectively?

The Writing Process Model

The model identifies three general components a) planning, b) translation, and c) reviewing (see the following illustration). Planning involves setting a goal for the project, gathering information related to this goal, which we refer to as research, and organizing this information so that the product generated makes sense. The goal may be self-determined or the result of an assignment. Research may involve remembering what the author knows about a topic or acquiring new information. Research should also include identifying the characteristics of the audience. What do they already know? How should I explain things so that they will understand? Finally, the process of organization involves establishing a sequence of ideas in memory or externally to represent the intended flow of logic or ideas.

What many of us think of as writing is what Flower and Hayes describe as translation. Translation is the process of getting our ideas from the mind to the screen and this externalization process is typically expected to conform to conventions of expression such as spelling and grammar.

Finally, authors read what they have written and make adjustments. This review may occur at the end of a project or at the end of a sentence. Authors may also solicit advice from others rather than relying solely on their own review.

One additional aspect of the model that should not be overlooked is its iterative nature. This is illustrated in the figure, which presents the model using arrows. We may be tempted, even after an initial examination of this model, to view writing as a mostly linear process – we think a bit and jot down a few ideas, we use these ideas to craft a draft, and we edit this draft to address grammatical issues. However, the path to a quality finished product is often more circuitous. We do more than make adjustments in spelling and grammar. As we translate our initial ideas, we may discover that we are vague on a point we thought we understood and need to conduct further research. We may decide that a different organizational scheme makes more sense. This reality interpreted using our tool metaphor would suggest that within a given project we seldom can be certain we have finished the use of a given tool and the opportunity to move back and forth among tools is quite valuable.

This model describes the processes identified by Flower and Hayes, but ignores two other components. The first is the writing task, which consists of the assignment and any writing completed at a given moment. The other missing element is the long-term memory of the writer. The long term memory or existing knowledge provides a source of information and strategies that the writer can use without resorting to new research. 

Hayes (2012) updated this model to incorporate additional research and comments from colleagues and his own laboratory. Later work placed a strong emphasis on both revising the planning component and subsequent drafts, as well as on the role of working memory. Working memory recognizes that cognitive capacity is limited, meaning activities must fit within the existing capacity or perhaps be ignored. Processes become less demanding less capacity as a function of practice and aptitude and among other topics, is vital in understanding changes that could occur for learners across the grade levels. For example, Hayes noted that keyboarding is more difficult for younger learners than handwriting and products produced on a computer would thus appear of lower quality. Differences in cognitive demands do change with experience with keyboarding, eventually becoming less demanding than handwriting. Other factors can also impact cognitive demands and in one example, Hayes noted that studies requiring adults to write in all caps reduced the quality of the final product because transcription in this form is less practiced. As an aside, I could not help recognizing the tendency of some to write in all caps on social media and my perception of the quality of what is produced in that format. Anyway. Finally, Hayes recognized that writing was a motivated activity and differences in motivation could emphasize the processes.  

One of the significant patterns in writing proficiency Hayes and others (Bereiter & Scardamalia, 1987) associated with the limited capacity of working memory and the gradual development of proficiency in the cognitive writing subskills, was the tendency to move from what Hayes and others describe as knowledge telling to knowledge transforming. The first approach results in a dump of ideas from long term memory triggered by the assignment and information that has already been recalled. In other words, a product can be generated without changing what is stored in memory or how this content is organized. Most instructors have a feeling for how this works. They have asked students to reply to an essay question and received at least some responses that seem to be everything students knew about the topic rather than a specific answer to the question. It can be hard to know if the student thinks they have answered the question or if this is just a frequently productive ploy. It is the first situation that shares characteristics with the idea of knowledge telling.

In contrast, writing classified as knowledge transforming requires that previously stored information be reorganized, reinterpreted, or extended based on speculation or insights. The writing task sometimes determines the difference, but transforming is more demanding and, when expected, is more likely to be produced by more capable writers. Writing to learn could involve either output, but the greater manipulation of ideas in knowledge transformation reflects the most significant benefit. 

Klein (1999) offers a review organized around the writing processes hypothesized to be responsible for learning. A brief summary of some insights from this paper provides examples of tasks and skills that differentiate knowledge telling from knowledge transforming, also relating the distinction to the processes involved. 

1. Point of utterance (no revision and limited planning). This explanation assumes that learning occurs in the attempt to generate comments on the topic (no revision or planning is expected). This category might be described as spontaneous writing – the learner is asked or personally commits to writing on a topic. An activity fitting within this category would be the five minute writing tasks some college lecturers assign at the end of a class. 
2. Genre-related – This explanation focuses on the benefits of transforming ideas to the structure demanded of a specific genre. For example, in a “position paper,” a writer is expected to take on of several possible positions are generate an argument supporting this selection. In selecting, organizing, and connecting knowledge to fit the demands of a formal writing task, the learner creates an understanding that would not exist without the imposed task.
3. Backward search – This explanation assumes that skilled writers formulate complex goals (characteristics of the desired product, audience needs, etc.) and then rework existing knowledge in terms of these goals. This seems a more generalized version of the “genre-related” explanation, requiring more sophisticated and complex problem-solving.

My own writing is generally linear with backtracking depending my assessment of how well things are going. This impression is based on my own behavior and may not accurately reflect the ideal recursive approach. When I take on a project, I assess what I already know and have notes on a topic and then read and take notes on additional material. I generate a rough idea of how these ideas could be organized (some would create a formal outline) and begin developing a draft. Often, I realize I need to fill a hole in my mental outline or find a reference in support of what I am trying to accomplish and have to take a closer look at my large collection of digital notes or read and take notes on another source or two. Upon completion of this initial draft, I reread what I have down to take care of lower level deficiencies (spelling, grammar) and often to add a little more material here or there so the document makes more sense or hangs together better. When writing for myself and without an external reviewer, I tend not to make major structural revisions. However, when I submit a paper for review, I do sometimes have to make larger adjustments even if the content is deemed useful. 

Where does AI play a role? Where should AI play a role? I have worked through my thoughts on these questions based on my own circumstances and also on what should be the circumstances for those in more formal learning settings. I want to produce content that meets a reasonable standard of quality, but I am not that interested in becoming a more accomplished writer. I want what I write to be a reflection of my experiences and what I have learned, and I assume I can learn from the process of writing. I am willing to invest time in this objective. I propose that others generate a similar analysis for themselves based on personal goals or goals for others they may be responsible for educating. 

How do I use AI? I primarily use AI to facilitate the research and planning components of my writing process and to perform some of the revision tasks. These emphases are consistent with my desire to learn from writing and my lesser interest in improving my writing skills. I am not suggesting everyone apply my priorities, I am suggesting it is possible to identify priorities and use AI strategically and efficiently.

Here is how this works. I have developed a large collection of notes consistent with methods of personal knowledge management and a technology-enabled second brain. This is a multidecade-long process that involves reading widely in the educational technology and educational psychology literature. When I get an idea for a writing project, I use AI to query this body of content for ideas related to my intended project. Based on the content I produce and queries for related information (some generated by AI), I review this new content and supplement my notes on the topic. I then often use AI (typically NotebookLM) to provide a structure for the intended project based on my collection of notes. I consider this proposed approach when generating my initial draft.

I use Grammarly heavily when I write. I use the pro version so I get constant feedback not only on spelling and basic grammar, but also more substantive recommended changes at the paragraph level. Grammarly identifies issues I should consider and offers suggestions. I suppose this could be a valuable learning opportunity, but I admit I just select the recommend changes that sound good. Grammarly has just pushed a major update that offers even more capabilities, but I have yet to explore which might be useful to me. 

The use of AI for research, planning, and text revisions do not limit my writing to learn. I think it is quite reasonable to associate AI capabilities with specific components of the writing process model, as applied to writing and writing to learn, in order to accomplish tasks that are not essential to developing writing skills or learning opportunities. The stickier problem presents itself when you must consider how to control the use of AI. 

Sources

Bereiter.C. & Scardamalia, M. (1987). Two models of composing processes (pp. 1-30). In C. Bereiter & M. Scardamalia (Eds) The psychology of written Composition. Erlbaum. 

Flower, L., & Hayes, J. R. (1981). A cognitive process theory of writing. College composition and communication, 32(4), 365-387.

Hayes, J. R. (2012). Modeling and Remodeling Writing. Written Communication, 29(3), 369-388. https://doi.org/10.1177/0741088312451260

Klein, P. D. (1999). Reopening inquiry into cognitive processes in writing-to-learn. Educational Psychology Review, 11, 203-270.

I was excited when Google announced its investment in developing NotebookLM as a tool for learners. First, I encountered the description of its new program Learning Your Way, which promised to personalize textbooks in various ways, including explanations based on personal interests. Examples of what this would look like were provided, but to submit your own content for the “learn your way” treatment, you first had to indicate your interest and then wait to be selected. I am still waiting. However, Google has also announced enhancements for the existing NotebookLM that make several proven study strategies more straightforward to implement, as well as a couple of unique ways to repurpose instructional text as a podcast or something resembling a slide-based lecture. The updates available to all are what I will describe here.

Before anyone gets overly excited, what Google can presently make available requires that an instructor or a learner must be able to load content into NotebookLM. There is no legal way in which what I will describe can be done with your existing commercial paper or even digital textbook. Companies producing instructional materials may either collaborate with tech companies or develop similar capabilities, but they are not doing so at present. I wrote a couple of textbooks earlier in my career. When my collaboration with a textbook company ended, I was given complete control of the copyrights and now I have full-length chapters I can use for demonstrations. This is what I am doing here. NotebookLM notebooks can be shared and I will make the content on which this tutorial is based available for you to explore. 

For those unfamiliar with the newest updates, NotebookLM presents as three vertical panels. The leftmost panel shows the content you have uploaded to NotebookLM as well as provides the opportunity to upload additional content and open individual files for viewing. The middle panel is where AI prompts are applied and the output from such prompts are displayed. The rightmost panel is where the older and new AI tools are activated and output from these tools can be accessed for later display. 

As soon as NotebookLM is launched, the middle panel displays a summary of the source files that have been added. Loading source files does not include them in this summary unless they have been selected (see check box). NotebookLM was developed as an RAG (retrieval-augmented generation), which means the prompts are applied to the content you provide rather than applied to a massive corpus available to the model. The new “Discover” tool available from the top of the sources panel breaks with this approach and allows a user to request additional information intended to be related to the purpose for a particular notebook that can be reviewed and added as an additional source. 

Before I continue, I want to identify one frustration I have with the way NotebookLM fits into my workflow. Developers have specific applications in mind when creating applications, and their vision may not include what an individual user prefers. My preference is to read, highlight, and annotate content before using an AI tool. While NotebookLM allows access to sources, it does not support highlighting or annotation, nor does it display such added layers from uploaded material. The workaround is to export personal additions and add this content to NotebookLM separately. 

Mindmap

New capabilities appear in the right-most column. The audio overview (podcast) and Mindmap capabilities were already available and will not be covered here. 

Quiz

The new tool that first caught my attention was the quiz. I have explored various ways to have LLMs ask questions about designated content, but having a built-in tool for doing so is unique. The tool generates a double-digit set of multiple-choice questions that are then stored as an associated resource. I have no idea why the number of items varies. When selected, the MC questions are displayed one at a time (see the following image) and then, no matter which alternative is selected, a comment is provided. The “explain” button (see red box in the following image) shows the content from the text associated with that question. If you want more questions, the set generated can be deleted and a new set generated. 

I think it is valuable when using this tool to be aware of your reaction and recognize you are working with an AI tool. As someone who had to generate multiple-choice questions for actual student exams, knowing what I know about student reactions, I would not use some of the AI-generated questions on an examination. I thought the stems of some AI questions were kind of vague or misleading, but the explanation clarified the logic justifying a given answer. If you understand this and are using the questions as a study experience, the ambiguity is probably fine. As a final comment to this post, I will explain why I prefer to ask an AI tool to generate open-ended (essay) questions on a specific topic and then wait to evaluate my response. Interacting with content in this way is more helpful. 

Flash Card Tool

Flash cards are a useful tool for implementing memory enhancement strategies such as retrieval practice and interleaving. While relying completely on flashcards would not be wise, this approach is effective and useful for quick reviews spaced over time. Again, the “Explain” button (see the second of the following images) offers a connection to the original content and this provides potential opportunities to review beyond simply verifying that a response is correct. Recognize that NoteBookLM generated 69 cards for the targeted chapter, so this tool covers the content in detail. 

Video Overview

The video overview offers what seems like an extension of the existing audio option. It strikes me as the equivalent of a lecture based on a series of slides. So imagine a large lecture environment in which you see the screen on which an instructor is projecting her PowerPoint and you are hearing the audio but not seeing the presenter. Having written this chapter, it is an interesting experience watching a lecture based on your words. It is possible to download the video so I decided to offer this download through YouTube if want to see an example. 

Just Use Chat

NotebookLM, before these built-in tools, was a way to interact with uploaded content using AI chat prompts. I find this capability more powerful than the tools that seem to recreate standard study experiences. The familiar tools are probably a way to engage less experienced learners, but I would argue that concepts such as debating and tutoring offer opportunities that take advantage of the language capabilities of LLMs. The following is an example of a chat I had with the content.

[Prompt] Ask me a short-answer question about generative tasks and wait to evaluate my reply

According to the sources, what two specific categories of generative activities are highlighted for their value in improving understanding, retention, or transfer, and what general type of content processing is involved in these activities?

——————————————————————————–

I will now wait to evaluate your reply.

[Learner reply] I remember the chapter talked about responding to questions and I can’t remember another example from the book. How about writing to learn, but I don’t think that was in the chapter.

[AI response] That was a strong attempt, and your intuition about “writing to learn” was very close to one of the specified terms!

Here is the answer to the question, based on the specific terminology used in the sources:

The two specific categories of research emphasizing generative activities that improve understanding, retention, or transfer are labeled as:

1. “Authoring to learn”

2. “Teaching to learn”

These activities involve a “generative processing of content”.

Your suggestion of “writing to learn” is directly supported by the text, as “authoring to learn” is described as involving the preparation and implementation of writing tasks. This generative processing of content is suggested to be superior in many ways to studying only for personal use.

While responding to questions is certainly a critical activity discussed in the sources—often serving as an external strategy for evaluation and regulation that compensates for weak metacognition—it was not one of the two specific research categories given the label “generative activities” in this context.

[ Added comment] What is not visible in my copies of this text from this interaction are the inserted numbered buttons that provide access to sections of text from the original text.

---

Notebooks can be shared. You are invited to explore the Notebook that was the basis for this prompt.

In K-12 education, writing often takes a backseat to other academic priorities. Elementary education is dominated by math and reading, while secondary education spreads its focus across a wide range of subjects. Unfortunately, this distribution of attention has left the development of writing proficiency hindered by several factors.

Limited Time for Writing Practice

One significant issue is the limited time students spend on writing activities, both in and out of the classroom. Research shows that only about 25% of middle school students and 30% of high school students meet the recommended minimum of 30 minutes of daily writing practice. Writing assignments at these levels are often brief, typically a paragraph or a short essay, with few opportunities for more complex projects that require synthesizing ideas from multiple sources.

While initiatives like “writing across the curriculum” aim to increase writing opportunities and integrate writing into other subjects, many teachers outside of language arts lack the training to effectively incorporate writing into their instruction (Picou, 2020). This lack of preparation, combined with time constraints, contributes to disparities in writing proficiency, as reflected in differences in NAEP scores across schools (Mo & Troia, 2017).

The Broader Benefits of Writing

Writing is not just a skill—it is a multifaceted process that integrates numerous subskills and offers significant cognitive and academic benefits. However, these benefits are only fully realized when students receive meaningful feedback on their work. Unlike other disciplines, evaluating written work is particularly time-intensive for educators, which may discourage frequent and substantive writing assignments.

Beyond skill development, writing also serves as a powerful tool for learning. Often referred to as “writing to learn,” this process involves cognitive demands that enhance understanding and retention (previous post). Writing tasks act as generative activities, externalizing thought processes and encouraging deeper engagement with the material. For example, when students are asked to provide personal examples of a concept, they connect prior knowledge to new ideas, fostering meaningful learning.

Two types of writing tasks stand out in their educational value: writing to explain and writing to persuade.

1. Writing to Explain
   This task requires students to learn something and then articulate their understanding through writing. The act of externalizing knowledge serves as a form of self-assessment, revealing gaps in understanding and prompting further learning. This process, often linked to metacognition, helps students refine their knowledge as they work to organize and express their ideas. As educational psychologist Graham and colleagues (2020) note, writing to learn has consistently been shown to enhance academic outcomes.
2. Writing to Persuade
   Persuasive writing involves crafting a position, supporting it with evidence, and addressing counterarguments. Despite its importance in developing critical thinking and reasoning skills, persuasive writing accounts for only about 20% of writing-to-learn tasks. This is a missed opportunity, as persuasive writing offers concentrated practice in analysis and argumentation, much like debate, but in a more efficient format for classroom use.

The Impact of AI on Writing Development

While writing is already underutilized in education, the rise of AI tools presents a new challenge. Educators are grappling with how to integrate AI productively without further reducing the time students spend writing. If AI tools are used to complete writing tasks for students, the generative benefits of writing—such as critical thinking and cognitive engagement—may be lost.

As someone who uses AI tools daily, I recognize their potential to enhance productivity and creativity. However, I also understand the risks. For example, I use AI to interact with a personal corpus of notes, allowing me to explore ideas before writing. This approach complements my writing process rather than replacing it. Students, however, may lack the motivation or understanding to use AI in similarly constructive ways. Under time pressure, they may rely on AI to bypass the cognitive effort required for writing, undermining the development of essential skills.

Addressing the Challenges

One strategy that I think would address both writing challenges would require an increase in supervised classroom writing. Such tasks could be improved with collaborative writing activities that included peer editing and revision. The peer responsibilities would include attention to both writing quality and content accuracy when the task is a writing across the curriculum task.

Moving Forward

The challenges facing educators are undeniably complex, and the rise of AI adds another layer of difficulty. However, ignoring these realities will not improve the situation. Writing remains a critical skill, both as a standalone competency and as a tool for learning across disciplines. By increasing classroom writing opportunities and leveraging collaborative approaches, educators can help students develop the skills they need to succeed in an AI-driven world.

I welcome your thoughts on this analysis and any ideas you might have for addressing the interconnected issues of writing development, AI integration, and educational priorities.

Sources

• Graham, S., Kiuhara, S. A., & MacKay, M. (2020). The effects of writing on learning in science, social studies, and mathematics: A meta-analysis. Review of Educational Research, 90(2), 179-226.
• Mo, Y., & Troia, G. A. (2017). Predicting students’ writing performance on the NAEP from student- and state-level variables. Reading and Writing, 30(4), 739–770.
• Picou, A. (2020). Are schools making writing a priority? New study shows students are not spending enough time. The Learning Agency Lab

Everyone needs to be aware of confirmation bias. This cognitive tendency is responsible for our focusing more on those ideas and facts that support our existing way of understanding the world. It applies to what information we select when given a choice and to the information that “sticks” when perceived. When I try to explain the second issue, I often describe what we already know as a model or perhaps an outline and new information that fits with this model or outline is easier to store and recall. This characteristic of human information processing is described as a bias because it argues that we find information that does not fit our existing way of seeing the world as less likely to influence us. We might argue we are open minded, but we still must work to identify and process challenges to existing ways of thinking.

Technology has long been argued to work in ways that support confirmation bias. Back in the early days of online search, there was a concern for what was called a filter bubble. This was the notion that search engines tracked our preferences and would bias hits appearing early in the list of possible sources based on our past choices as we responded to search results. Did we select results from the top of the response list or not? I read about this “problem” and struggled to find a way to test it. After reading accounts of the problem, I decided I could use my own online history as a test. I spent a lot of time searching and reading about technology and had made use of Apple equipment for years. It occurred to me that the word Apple was ambiguous — it could mean a computer company or a fruit. I reasoned that if I searched anonymously and when using a browser aware of my identity and searched for “apple” I should get different hits at the top of the search results. The results were fairly inconclusive and always favored computers. I may have been wrong about anonymous searchers, or perhaps just the notion that more people would want to know about apple the fruit.

AI and Confirmation Bias

I have tried to identify ways in which AI prompts might generated personally biased responses and started with some searches. The first warning I discovered argued that the prompts themselves could be an unrecognized problem. Psychology Today reported that Confirmation Bias could already exist at the stage of writing a prompt, so of course, the response from the AI tool would attempt to provide the information requested.

A recent announcement from ChatGPT led me to explore a different possibility. The new capability involved the opportunity to turn history on and off. I am still not certain of the intent of this control, but it got me thinking about the filter bubble issue I had tried to investigate in the early 2010s.

Before trying my original internet history strategy, I thought I would just ask ChatGPT about potential bias. If you just read the following, you may not note what I did, but it was clear that the AI tool knew quite a bit about me and used this information in responding.

Here is the reply to my prompt:

Great question, Mark.

When history is turned on, ChatGPT uses your prior conversations and context across sessions to tailor responses more personally. When history is off, each prompt is treated in isolation, with no memory of past conversations or preferences. Here’s how that difference plays out:

? With History ON

• Personalization: ChatGPT may remember your preferences (e.g., your interest in educational psychology, your writing style, your teaching context) and adapt replies accordingly.
• Continuity: It can refer to earlier parts of a conversation or even previous sessions if memory is active (e.g., remembering that you’re revising a specific slide deck).
• Efficiency: You don’t have to reintroduce background details repeatedly; the system can “pick up where you left off.”
• Persistent memory (if enabled): You can allow ChatGPT to remember things long-term, like your goals or recurring projects.

? With History OFF

• No personalization: ChatGPT won’t recall your identity, preferences, or past queries.
• Each prompt is standalone: Even within a single session, it treats each message without prior context unless you include it explicitly.
• Privacy-first: The content of your chats won’t be stored or used to improve models.
• More generic answers: Responses will tend to be more neutral or general-purpose since there’s no way to reference or build on prior knowledge.

? Same Prompt, Different Responses

Let’s say you prompt:

“Give me three ways to explain working memory to pre-service teachers.”

• With history on, ChatGPT might recall that you’re preparing a university-level course for future educators and tailor examples accordingly (perhaps referencing your slide deck or prior discussions of models like Baddeley & Hitch).
• With history off, it might assume a general audience and provide broader educational examples (e.g., working memory in classroom tasks like copying from the board or doing mental arithmetic).

Aside from the information itself, note several indicators it was tailoring the response to me. It identified my vocation as an educational psychologist. It used examples that would be helpful to someone who wanted to understand a general topic based on their background. So, it used educational examples.

Back to the “Apple” test.

I wanted to generate my own test of biased feedback and tried a version of the approach I had tried with search results. I tried to think of a topic I approach in a unique way and that might bias an AI response based on my personal history.

I am interested in the use of digital technology that seems different from more popular representation. For example, should class notes be taken by hand or on a laptop? Should people read from paper or a tablet screen? I think I can make a case for a digital approach because it is easier to store and utilize by-products of experiences over extended period of time. So digital notes and highlights can be exported and retained in ways that are easier to search, interrelate, update, etc.. Yet, this is not position taken in public sources offering advice to students, teachers, and decision makers.

My history of prompting AI to offer content are biased by my way of viewing such issues. For example, I might use the following prompts:

I am interested in comparing note-taking by hand and on a digital device. What are the advantages of digital notes when those notes are intended for use over an extended period of time

I am interested in comparing note-taking by hand and on a digital device. What are the advantages of digital notes when the goal is to discover connections among ideas recorded on different systems

Now for my test. What if I create a more neutral prompt and submit this prompt with my history turned on and off?

Summarize the research comparing note-taking by hand and on a laptop. What should a college instructor recommend?

With memory on

Research comparing handwritten and laptop notetaking focuses on how each method affects learning outcomes such as comprehension, retention, and conceptual understanding. Below is a summary of the key findings and instructional implications.

Key Research Findings

1. Encoding vs. External Storage

• Notetaking supports learning through encoding (processing while writing) and external storage (referring back to notes).
• The method of note-taking influences encoding quality more than external storage.

2. Handwriting Promotes Deeper Processing

• Mueller & Oppenheimer (2014): Students taking notes by hand performed better on conceptual questions than those using laptops.
• Explanation: Typing leads to verbatim transcription, while handwriting encourages summarizing and processing.
• Follow-up studies confirmed that handwritten notes promote deeper understanding, especially for material requiring synthesis or inference.

3. Laptop Notetaking and Verbatim Transcription

• Laptop users tend to transcribe lectures verbatim, which is a shallower form of processing.
• Even when told to avoid verbatim notes, laptop users often struggle to summarize effectively.

4. Distraction and Multitasking

• Laptops introduce distractions: Web browsing, messaging, and multitasking impair learning for both the note-taker and nearby students.
• Sana, Weston, & Cepeda (2013): Nearby students also performed worse when seated near multitasking laptop users.

5. Volume vs. Depth

• Laptops allow more content to be recorded, but more content doesn’t always equal better learning.
• Handwritten notes tend to be shorter, more selective, and encourage rephrasing, which benefits comprehension.

6. Review and Revision

• Laptop notes are easier to organize, search, and revise, which can aid long-term study.
• Handwritten notes may encourage memory consolidation, especially when rewritten or summarized later.

Recommendations for College Instructors

1. Promote Purposeful Notetaking

• Encourage students to summarize and paraphrase regardless of method.
• Teach effective notetaking strategies such as the Cornell method or concept mapping.

2. Consider a Handwriting Default

• Suggest handwriting for lectures emphasizing conceptual understanding or discussion.
• Provide explicit rationale (e.g., “This will help you understand and remember better”).

3. Allow Laptops with Conditions

• If laptops are allowed, encourage use of apps that limit distractions.
• Consider designating laptop zones to reduce spillover distraction.

4. Support Note Review

• Promote post-lecture activities: reviewing notes, rewriting, or using notes to answer practice questions.
• Share outlines or slides to reduce pressure to capture everything.

5. Adapt to Context

• For highly detailed or technical lectures (e.g., coding or statistics), typing may be more efficient.
• Consider hybrid approaches (e.g., typed notes with handwritten annotations).

Final Takeaway

Recommendation: Encourage handwritten note-taking when feasible, especially for classes involving complex reasoning or discussion. If laptops are used, guide to avoid verbatim transcription and minimize distractions. Whatever the method, emphasize that note-taking is a learning activity — not just a record-keeping task.

Would you like citations or slides to support this summary in a teaching context?

— — — — — —

With memory off

Summarize the research comparing note-taking by hand and on a laptop. What should a college instructor recommend?

Sure! Here’s a concise summary of the research comparing hand note-taking and laptop note-taking, plus a recommendation for college instructors:

Research Summary:

• Handwritten notes tend to enhance learning and retention better than typing notes on laptops.
• Writing by hand encourages processing and summarizing information, leading to deeper understanding.
• Laptop note-taking often leads to verbatim transcription, which can reduce comprehension and critical thinking.
• Some studies find that laptop users are more easily distracted by unrelated activities (social media, browsing).
• However, laptops allow for faster note-taking and easier organization or review, which can benefit some students, especially those with certain disabilities or faster speaking lectures.

Recommendation for College Instructors:

• Encourage students to take handwritten notes, especially for conceptual understanding and long-term retention.
• If laptops are allowed, instructors should coach students to avoid verbatim typing and focus on summarizing.
• Consider a hybrid approach: use laptops for occasional digital resources, but emphasize active listening and synthesis in notes.
• For accessibility, allow laptop use when needed but promote best practices to maximize learning.

Would you like me to draft a brief instructor note or syllabus statement based on this?

Comparison Summary

You can examine these two responses and reach your own conclusions. My interpretation is very possibly biased by my effort to demonstrate an impact of history. My analysis follows.

1. Without access to personal history, the prompt response is significantly shorter. This was predicted when I asked ChatGPT directly about what to expect with history on and off.
2. I would say the response with personal history on still favors nondigital notes, but there is more recognition of differences and some concessions to situations in which digital content may provide an advantage.

So what?

I think it possible to argue both approaches demonstrate a type of bias. Perhaps there is value in understanding this and recognizing that the individual prompting the AI must still be sensitive to personal bias. Simple prompts may also elicit simple responses, and more sophisticated issues end up being ignored.

I have been exploring and writing about AI now since the release of ChatGPT. I think about AI both as a user and as an educator and believe I have enough experience and a perspective from which to offer an overview. The tools have improved to a level at which I find them quite valuable as a research and writing assistant. My main approach is to use a tool that allows me to interact with my own digital notes collected over maybe a decade to assist in many of my writing projects. I count myself among those who advocate for the professional value of AI.

My thoughts on AI in education are more complex and it is this perspective I will try to share here. Let me start with what I think is an essential assumption and that is students will find ways to use AI. Whatever the perspective of individual educators is, I argue it is necessary to begin accepting this assumption. Trying to think across many different content areas and skills, it seems reasonable to stipulate that there are certain skills that must be practiced directly to develop (e.g., writing, reasoning, problem solving) and elements of information that may not be life changing whether retained in an individual’s memory or not, but that the general benefit of existing knowledge which is about stored information and the connections that exist within this information offer advantages in understanding and reasoning. Any given fact can certainly now be searched when needed, but this option does not account for the general benefits of what I would describe as general knowledge. We accumulate general knowledge by interacting with our world, but the purposeful accumulation of important information is more efficient through the process we commonly call education. Let me add one more assumption to this position statement. We cannot learn for others nor can we make them learn. We can at best provide access to information and provide external tasks that have the potential to influence the processes of learning. Ultimate responsibility must be placed on individual learners and this is often a requirement at a time when individual learners lack the background and perhaps cannot make decisions understanding how learning works and how skills and knowledge may influence their futures. 

Here is my thinking about AI. Educators have a limited amount of time during which they can directly influence learners. They must depend on the cooperation of learners and perhaps their parents when attempting to influence learning during other times. I would describe this reality as important in making decisions about how this time of maximum influence will be spent. For example, I write a lot about study behavior. Educators and sometimes do use class time for studying. When they make this commitment, they are also reducing the time available for other experiences – presentation of information, experiences such as science labs, peer interactions such as guided discussions and debate. Some reactions to AI suggest that class time be used to some extent to control the use of AI. For example, writing a theme during class rather than at home or study hall or completing math problems during class rather than as homework. If the limitation of AI is determined to be significant enough, this can be done, but this will then replace other activities.

So, I believe that the development of some skills and a general knowledge base cannot be eliminated because of AI and this development can only be guaranteed during the time during which an entire class would have to be prevented from using AI. To be clear, I am not advocating for this option. I am trying to identify the benefits and costs of options which I believe cannot be individualized; e.g., educators cannot really differentiate what is required of different individuals in a classroom situation.

Much of what we are playing with involves decisions about when to attempt to exert control over personal goals and motivations. I was a university prof and there is a common approach at this level that differentiates the requirements for a major from general education requirements. We don’t allow students to decide if they want to develop basic writing skills because we require a couple of semesters of composition. We expect a basic level of function in mathematics, but allow individuals to make decisions as to whether the basic course will be what amounts to a high school level course in algebra or the Introduction to The Calculus. 

How strongly do we as educators believe we should ignore personal goals and motivation? This is a question for us and for other stakeholders in the educational process. We certainly cannot control learners, but we can arrange evaluation processes to recognize when some mandatory proficiency has not been achieved. Politicians and the general public already tend to blame educators when basic proficiencies do not match those existing in other countries or when graduates seem unprepared for vocations or for civic responsibilities. What consequences do those who are critical suggest for educators or what are they willing to tolerate for the learners who are ultimately responsible? 

When I write about this topic it becomes clear to me that the issues I address are very complex and perhaps that is a useful message for others who have simplistic positions on the process of education or the issues educators face. I am a big fan of research informing practice. One challenge with the type of issues described here is that most involve cumulative effects over an extended period of time. Longitudinal studies may eventually provide useful insights, but the downsides could impact an entire generation before the research makes this outcome clear.

Is a summary possible?

I am willing to say that AI offers great benefits to supplement human actions. We all should be prepared to take advantage and guided experience in developing AI-related knowledge and skills should now be a component of what we teach. 

Reliance on AI in place of tasks that develop skills is detrimental. You cannot learn to write if AI replaces your attempts to write. You cannot develop critical thinking or reasoning skills if you do not struggle with tasks that require these skills. The issue then is whether the skills are important to the individual and when is the optimal time to make this decision. Perhaps even this is too narrow of a perspective. What are the commitments each of us owes to each other when it comes to basic knowledge and skills?

If forced to take a position, I would suggest that individuals be required to learn and be able to develop knowledge and skills AI-unaided and be able to demonstrate they can apply AI in ways appropriate to the tasks they presently must accomplish. The notion of tool or augmentation seems useful here and it would seem curriculum developers could differentiate cognitive skills from tool proficiency accordingly. 

Note: I find that as I write about this topic I encounter the complexities that I think are important to consider. I certainly welcome comments that address these complexities and possibly provide me when ideas I can address in response.

My recent focus on losing an author’s perspective when consuming AI-generated content, particularly the AI response now preceding the typical hits generated by a search query, has encouraged a personal exploration of what might be a middle ground. I frequently use AI tools to chat with the notes and highlights I have generated in reading hundreds of journal articles and books. This body of content has a perspective of sorts because the notes I generate and the content I identify through highlighting reflect my personal way of viewing my field and represent ideas that both support and oppose scientific concepts and theories important to these topics. Any researcher who has relied on the accumulation of relevant articles over the years and makes use of PDFs rather than paper could do a similar thing to make extended use the content they have accumulated over the years. This accumulated body of content seems a great example of what the personal knowledge management advocates describe as a second brain. 

Here, then, is what I believe to be an interesting question. Do AI chats with personally curated content provide different insights than a similar AI chat without this curated focus? Perhaps a more concrete example would be a better way to communicate my issue. So, I have the highlights and notes I have accumulated from years of reading in a designated area (e.g., educational applications of cognitive psychology), and I can chat with this content using identifiable services (e.g., NotebookLM). Would the reply to a prompt applied under these circumstances yield different insights than the same prompt applied using an AI tool not focused on a designated body of content (e.g., Perplexity)? 

At first, this might seem a silly comparison. Certainly, one could find a biased assortment of resources taking a common flawed view on a topic, and then show that AI limited to consolidating this content would yield different prompt replies than similar prompts asked of an unfocused AI tool. But this does not seem to be what those building a second brain think they are doing. They would likely be offended by the suggestion that their efforts were for naught, and AI queries would yield more accurate information. They would probably suggest they are doing exactly the opposite. They are using their expertise to identify high-quality sources, and their notes would address both the strengths and weaknesses of the sources they curate. I am not certain the outcome of my proposed comparison is obvious. 

My Test Case

I write a lot about study behavior and have found the controversy involving whether learners are better off reading and taking notes using paper or digital content of some interest. While many researchers suggest paper is superior, my personal experiences and focus on the benefits of previous learning experiences over time, see a unique value in digital processing. Simply put, highlights and annotations saved and organized offer advantages over a year or 50 years later that most would find difficult to replicate with paper. Even over short periods, studying is more than simple review, and digital tools offer unique opportunities for “post processing”. 

The specifics here are important only if the type of information generated in pursuit of the information I encounter would change as a function of how I might use AI. I provide the background material because the topic could interact with the different uses of AI I identify in ways I cannot anticipate. Part of what I propose is that others with different collections of digital content might replicate the test I am applying to their own material and share their observations. There are so many uncontrolled variables I assume that while this is an interesting issue, personal preference will always be the deciding factor. Variations in topic, tool, and prompt could result in different conclusions. 

The Prompt I used follows. The variation of the prompt I used when engaging a non-focused use of AI simply eliminated the phrase “Using my notes and highlights”. 

Prompt: Using my notes and highlights, write a 400 word blog post comparing the advantages and disadvantages of reading and taking notes from paper and digital devices. 

I used the directed prompt with Mem.AI, NotebookLM, and Smart Connections (Obsidian plugin). Perplexity was used as the nondirected AI tool. I will offer my observations first and provide the full prompt responses at the end as Appendices.

Sources – Perplexity is unique in comparison to other chat tools in that it provides specific sources for comments it generates. These tend to be what I would call secondary sources (see list following the Perplexity example). In contrast, see the sources in the Mem.AI responses. The names that appear are a crude version of the citation method academics use to reference journal articles and books (which were the sources I highlighted and annotated). One way to think about this may be that Perplexity is accessing the summaries generated by various individuals who have read primary sources, while Mem is accessing my personal summaries of similar sources. If identifying primary sources is important, it is easier to do this when you can show what these sources were. 

Identification of unique insights – It would seem that an AI analysis based on specific notes, highlighting, and source selection would generate an output more useful for tasks you want to pursue. While obvious if the content of interest was selected with a task in mind and based on a small amount of material, this is not the way a “second brain” is built. The hundreds of sources I have collected represent a wide range of topics in my field. Specific topics of interest emerge within this process of more general learning, and part of the assumption in using a second brain is that the broader background will reveal connections that may not have been anticipated. The hope is that the application of AI, rather than basic searching, will help surface such connections. 

With the exception of the sources cited, much of the information in the two types of searches was similar. Perhaps asking for a 400-word blog post as an outlet was not the best way to reveal subtle differences. I will direct your attention to sections I have highlighted in the NotebookLM and Perplexity prompt responses. Both NotebookLM and Perplexity provide citations that do not appear when copying the text. Because I was looking for comments related to the use of content over time, I was paying attention to any mention of searching or other mentions of delayed activity. The Perplexity response did not offer a citation. The NotebookLM output mentioned export, organization, and search. In addition, there were multiple citations, and the linked citations identified notes and highlights in the digital form.

Summary

AI tools with various capabilities are now available. For those of us who read digitally, we have the opportunity to export highlights and annotations that can be stored over time. AI can be used to chat with this stored content. My interest here was an attempt to determine if there was a unique value in applying AI to such content in comparison to asking questions of AI without this targeting of curated information. 

I doubt the effort I describe here would convince anyone to change their existing strategy, but my hope is that I have offered an approach they might try to explore the options that are available. 

************

Appendices

Mem.ai

The debate between reading and taking notes on paper versus digital devices is a nuanced one, with research highlighting various advantages and disadvantages for each medium. While digital tools offer convenience and speed, traditional paper methods often promote deeper cognitive engagement.

Advantages of Digital Reading and Notetaking

Digital devices offer several benefits. For instance, digital note-takers tend to record more content, including more verbatim lecture strings, due to faster typing speeds compared to handwriting Luo et al 2018. This increased volume of notes can be beneficial for later review, especially when notes are not immediately studied Luo et al 2018. Digital platforms also facilitate collaborative note-taking, allowing students to share the cognitive load and potentially create more complete notes Courtneyetal2022. Furthermore, digital tools can offer features like multimedia integration and online research capabilities, enriching the learning experience Yamac et al 2020. For example, digital writing instruction with tablets has been shown to improve writing performance and knowledge in primary school students, partly due to features like class blogs and multimedia components Yamac et al 2020.

Disadvantages of Digital Reading and Notetaking

Despite the advantages, digital reading and note-taking come with notable drawbacks. A significant concern is the potential for distraction. Studies suggest that the perceived advantage of longhand note-taking in some research may be attributed to the distractions inherent in digital devices, such as web surfing and social media Voyer 2022 summary. This can lead to shallower processing of information SingerAlexander2017b. Research indicates a “screen inferiority” effect, where reading comprehension can be lower on digital devices, particularly for informational texts and under time pressure Delgado2018. This effect has even been observed to increase over time Delgado et al 2018. The lack of physical cues, like the feel of pages, in digital reading can also hinder the formation of a mental map of the text, impacting comprehension of chronology and temporality Mangen et al 2019.

Advantages of Paper Reading and Notetaking

Paper-based methods often foster deeper engagement and better retention. Handwriting, being slower than typing, forces individuals to process and summarize information, leading to a more generative encoding of knowledge MuellerOppenheimer2014. This deeper processing can result in better performance on conceptual questions 

MuellerOppenheimer2014. The physical act of writing and the tactile feedback from paper contribute to a stronger mental representation of the material Mangen et al 2019. For instance, studies have shown that paper readers are better at recalling “other relevant information” and performing better on questions related to key points SingerAlexander2017b.

Disadvantages of Paper Reading and Notetaking

While beneficial for deep processing, paper note-taking can be less efficient in terms of speed and volume compared to digital methods Luo et al 2018. It also lacks the inherent searchability and organizational capabilities of digital notes, which can make retrieval and restructuring of information more challenging SmartWisdom. Converting highlights from paper to more elaborate notes can also be a more cumbersome process Highlighting&fleeting.

In conclusion, the optimal choice between paper and digital depends on the specific learning goal and context. For tasks requiring deep comprehension and conceptual understanding, paper often holds an advantage. However, for efficiency, volume, and collaborative efforts, digital tools offer compelling benefits, provided distractions are managed effectively.

************

NotebookLM

Here’s a look at the advantages and disadvantages of reading and taking notes using paper versus digital devices, drawing from the sources provided:

The rise of digital devices has shifted how many people read and take notes. However, research comparing reading from paper and screens reveals a complex picture, with nuances depending on the text type, reader’s age, and even the specific device used. Several meta-analyses indicate a general advantage for reading comprehension when reading from paper compared to screens, particularly for informational texts. This paper advantage has even been found to increase over time. However, this difference is often not seen with narrative texts, and studies comparing reading on tablets specifically have sometimes found smaller or no significant differences compared to print.

When it comes to note-taking, there’s also ongoing debate about the best method. Some studies comparing handwriting and typing notes have found a benefit for handwriting notes, particularly for understanding concepts. This has been attributed to the slower speed of handwriting, which may encourage more summarization and paraphrasing rather than simply transcribing verbatim, leading to deeper cognitive processing. However, other research and meta-analyses have found inconsistent results or no significant overall difference between handwritten and typed notes. Some studies suggest that typing can lead to more complete notes, and note completeness can be related to better performance.

Digital tools offer powerful affordances for reading and note-taking, such as the ease of highlighting and adding annotations directly to the text. Digital notes and highlights can be easily exported, organized, and searched later. Digital environments also facilitate collaborative annotation and note-taking. However, digital environments can also present challenges. They may be more prone to distractions, and frequent use of digital media, particularly for quick interactions with short texts (like social media), may contribute to the development of shallow reading habits like scanning and skimming. Some online content may also have lower linguistic quality.

Ultimately, the effectiveness of reading and note-taking, whether on paper or digitally, depends significantly on the strategies and cognitive processes employed by the reader. While paper might offer some advantages for deep comprehension of informational texts and handwriting for conceptual processing, digital tools provide powerful functionalities for capturing, organizing, and retrieving information, as well as facilitating collaboration. Focusing on how one engages with the material and utilizes the tools, rather than just the tool itself, is likely key to effective learning.

The following is a screen capture of the original view of the highlighted section described above.

****************************

Prompt: Write a 400 word blog post comparing the advantages and disadvantages of reading and taking notes from paper and digital devices.

From: Perplexity

Comparing Reading and Note-Taking: Paper vs. Digital Devices

Choosing between paper and digital devices for reading and note-taking is a personal decision shaped by convenience, effectiveness, and lifestyle. Both formats offer distinct advantages and disadvantages.

Advantages of Paper

• Better Comprehension and Retention: Studies show reading from paper leads to higher comprehension and test scores. Students who read print books outperform those who read digitally, and handwritten notes often result in better memory retention compared to typing[1][6].
• Fewer Distractions: Paper books and notes keep things simple—no pop-ups, notifications, or temptations to multitask, which helps maintain focus[1][6].
• Emotional Connection: Many readers find a deeper emotional bond with physical books, appreciating the tactile experience and the satisfaction of seeing their progress[1].
• No Power Needed: Paper never runs out of battery and is always ready to use[1][6].

Disadvantages of Paper

• Storage and Portability: Physical books and notes take up space, can be heavy, and are cumbersome to transport, especially when traveling or moving[5].
• Accessibility: Finding a specific book or note can be time-consuming, and you must visit libraries or bookstores for new material[5].
• Environmental Impact: Paper production contributes to deforestation and environmental harm[5].
• Vulnerability: Paper can be easily lost, damaged by water or fire, and is harder to back up[5][6].

Advantages of Digital Devices

• Convenience and Accessibility: Digital libraries offer instant access to thousands of titles and notes, all stored on a single device. Searching for information is quick and efficient[3][4].
• Eco-Friendly: Digital reading and note-taking reduce paper usage and environmental impact[3][4].
• Interactivity and Multimedia: eBooks and digital notes can include videos, images, and interactive elements, making learning more engaging[3][4].
• Collaboration and Organization: Digital notes are easy to organize, search, and share. Real-time collaboration and version control are possible, which is ideal for group work[4].
• Accessibility Features: Text-to-speech and adjustable font sizes make digital content more accessible to people with different needs[3].

Disadvantages of Digital Devices

• Distractions: Devices can tempt users with games, notifications, and other apps, reducing focus[6].
• Lower Retention: Typing notes can lead to lower retention compared to handwriting, as it often encourages verbatim transcription without deeper processing[6].
• Dependence on Power: Devices need batteries and charging, which can be limiting in certain situations[6].
• Cost: Digital devices are more expensive upfront than basic paper and pen[6].

Conclusion

Paper excels in comprehension, retention, and simplicity, while digital devices shine in convenience, organization, and collaboration. The best choice depends on your priorities—whether you value focus and memory or accessibility and efficiency. Many find a hybrid approach, using both formats as needed, offers the best of both worlds.

Sources

[1] The benefits of printed books – Junior Library Guild https://www.juniorlibraryguild.com/blog/post/the-benefits-of-printed-books

[2] Benefits of Notetaking? | Student Skills Workshops https://sites.austincc.edu/student-skills-workshops/taking-effective-notes/benefits-of-notetaking/

[3] Top 7 Benefits of Digital Reading in 2025 – Kitaboo https://kitaboo.com/what-is-digital-reading/

[4] 6 advantages of digital note-taking: unleash your productivity https://beingpaperless.com/unleash-your-productivity-6-advantages-of-digital-note-taking/

[5] Paper Books Vs. Ebooks https://www.doradolist.com/blog/paper-book-vs-ebook/

[6] Typing vs. Writing: The Pros and Cons of Both Note-Taking Methods https://titantimes.live/2025/02/19/typing-vs-writing-the-pros-and-cons-of-both-note-taking-methods/

[7] Digital reading: Pros and cons of reading on devices – tablets & e … https://teachinginhighered.com/2017/09/11/digital-reading/

[8] Taking Digital Notes: The Pros, Cons, and Best Practices – Ask.com https://www.ask.com/news/taking-digital-notes-pros-cons-best-practices

[9] Evidence increases for reading on paper instead of screens https://hechingerreport.org/evidence-increases-for-reading-on-paper-instead-of-screens/

[10] Benefit of Handwritten vs. Digital Note Taking https://www.mrsblackwell.com/journal/note-taking

[11] Will you learn better from reading on screen or on paper? https://www.snexplores.org/article/learn-comprehension-reading-digital-screen-paper

[12] Unlocking the Brain: the Cognitive Benefits of Digital Note-Taking for … https://www.marshmallowchallenge.com/blog/unlocking-the-brain-the-cognitive-benefits-of-digital-note-taking-for-students-sounds-great/

[13] Advantages And Drawbacks Of Both Paper And Pixel Books https://tracycooperposey.com/paper-and-pixel-books/

[14] Digital Notes vs. Paper Notes: The Pros and Cons – SchoolHabits https://schoolhabits.com/digital-notes-vs-paper-notes-the-pros-and-cons/

[15] What are Top Pros and Cons of Online Reading in 2025? – Kitaboo https://kitaboo.com/pros-and-cons-of-online-reading/

[16] Digital vs. Handwritten Notes: Pros and Cons for Professionals https://leadavid.com/digital-vs-handwritten-notes-pros-cons/

[17] Reading On Screens vs Paper: Which Is Better? – Unplugged https://unplugged.rest/blog/reading-on-screen-or-print-which-is-better

[18] Paper vs. Screen: Note-taking at Dartmouth https://www.thedartmouth.com/article/2023/10/paper-vs-screen-note-taking-at-dartmouth

[19] The Advantages of Using a Digital Note Taking App – Box Blog https://blog.box.com/advantages-of-using-a-digital-note-taking-app

[20] Do Students Learn More by Reading From Paper or Screens? – EWU https://online.ewu.edu/degrees/education/med/reading-literacy/reading-from-paper-or-screens/

[21] Pros and Cons of Typed, Digitally Handwritten, and Paper Notes https://guts.wisc.edu/2020/11/19/pros-and-cons-of-typed-digitally-handwritten-and-paper-notes/

[22] Pros and Cons of eBooks: Is Digital Reading Right for You? https://www.wrightbookassociates.co.uk/blog/pros-and-cons-of-ebooks/

[23] Truth about Digital Note Taking vs Paper Notes (PROS/CONS) https://www.youtube.com/watch?v=4nw4Z2cwm30

[24] PROOF POINTS: Paper books linked to stronger readers in an … https://hechingerreport.org/proof-points-paper-books-linked-to-stronger-readers-in-an-international-study/

[25] [PDF] Reading on paper and screens: advantages, disadvantages, and … https://pdfs.semanticscholar.org/f5d3/be4309ea16cede980900c13e65ac48aad6d3.pdf

[26] Pros and Cons of Digital vs. Traditional College Textbooks https://www.honorsociety.org/articles/pros-and-cons-digital-vs-traditional-college-textbooks

[27] Reading on Screens Worsens Comprehension for Younger … https://www.edweek.org/teaching-learning/reading-on-screens-worsens-comprehension-for-younger-students-what-can-teachers-do/2024/01

[28] 7 Scientific Benefits of Reading Printed Books for Better Brain Health … https://www.howlifeunfolds.com/learning-education/7-scientific-benefits-reading-printed-books

[29] Evidence increases for reading on paper instead of screens: Most … https://www.reddit.com/r/books/comments/n3uc66/evidence_increases_for_reading_on_paper_instead/

[30] 10 Benefits of Reading Print Books, According to Science https://www.realsimple.com/health/preventative-health/benefits-of-reading-real-books

[31] The important thing is to read. Advantages of digital reading https://richmondsolution.com/en/ventajas-lectura-digital/

[32] Digital reading: benefit or risk for child literacy? https://school-education.ec.europa.eu/en/discover/news/digital-reading-benefit-risk

[33] Turning the Page: What Research Indicates About Print vs. Digital … https://oej.scholasticahq.com/article/125437-turning-the-page-what-research-indicates-about-print-vs-digital-reading

[34] E-books vs Printed Books: The Disadvantages of E-books https://web.4hatteras.com/hatteras-news/e-books-vs-printed-books-the-disadvantages-of-e-books

[35] The benefits and drawbacks of reading digitally https://webbcanyonchronicle.com/9378/scienceandtechnology/the-benefits-and-drawbacks-of-reading-digitally/

*****