#439 – The Continued Evolution of NotebookLM

#439 — The Continued Evolution of NotebookLM

AVID Open Access
9 min

Transcript

The following transcript was automatically generated from the podcast audio by Otter.ai. Because of the automated nature of the process, this transcript may include unintended transcription and mechanical errors.

Paul Beckermann 0:00 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. What’s in the toolkit? Check it out.

Paul Beckermann 0:16 The topic of today’s episode is the continued evolution of Notebook LM. This is not the first Tech Talk for Teachers episode dedicated to Notebook LM, and that’s for good reason. It’s a powerful and student-friendly digital notebook that’s integrated conveniently into the Google Workspace ecosystem. Since my last episode focused on Notebook LM, Google has added several features that have made this tool even more powerful. So today, I’m going to review the top six features of Notebook LM and give you ideas for how both you and your students might use these features.

Number one: targeted content. One of the most powerful aspects of Notebook LM is that it allows you to load your own documents, links, resources, websites, and videos into a specific notebook. Because you are gathering the content and defining the knowledge base, your interactions with the AI in Notebook LM are source-grounded.

This means the responses that you get are based only on the material you have provided. This gives you so much more control over the depth and breadth of the content and topics being discussed, and because the source content is defined, it minimizes hallucinations and ensures accuracy.

Once you’ve built your notebook, you can then ask questions and get answers based on that defined content. Here are a few ways teachers might use this capability: upload and unpack academic standards and curriculum, develop lessons based on specific standards, analyze an article or short story, summarize research into bulleted points, pull out top takeaways from a collection of related articles, or generate test or discussion questions based on source content.

Students, on the other hand, might translate text or generate a summary in another language, simplify complex documents into a shorter summary, or generate math problems for practice based on an example or chapter. Ask questions about literary text, ask questions about a historical event, upload an assignment, and brainstorm ideas for how to complete it. Well, of course, it’s really up to you and your students to define the parameters for how you’ll use this in your classroom.

Number two: audio and video overviews. The audio overviews has been part of Notebook LM from the beginning. This feature generates a podcast version between two people discussing and thereby summarizing the content of the notebook. It sounds very realistic and is easy to listen to and understand. The video overview is a new take on the audio overview. The videos are narrated by a single voice, rather than two people in conversation. The videos also add a visual element, usually in the form of images or pull quotes. Because there are two options, you and your students can decide which output best meets your needs. As for uses, teachers could use this to summarize reports, chapters, or research documents.

Students can use this to get general summaries of research that they’re conducting, or possibly to help them process a textbook chapter.

Number three: Mind Map. This is one of the new features of Notebook LM. Based on the content you’ve selected, the AI will produce a branching mind map which breaks down and outlines the content. For instance, when I uploaded a collection of documents about designing blended learning playlists, the Mind Map broke that top level topic into four sub parts: definition of blended learning, blended learning models, playlist model overview, and playlist templates and formats.

This is really helpful for getting a big picture understanding of the content available. Each of the four subtopics that were generated included an arrow to its right. By clicking an arrow, the topic branches again. For instance, a click on playlist model overview revealed the sub points: definition, criteria, and design steps.

Again, I could click the arrow by any of those items and dig even deeper and expose another layer of subdivisions. You can go as far as you want. Teachers could use this to break down their academic standards, curriculum resources, or even research for their own college class. Students could use it to break down and simplify nearly any academic content or resource that they have access to. It can quickly give them high level understanding of how a topic is broken down, an understanding that can help them mentally organize and make sense of that new information.

Number four: reports. This is another new feature. By clicking this option, you’re presented with multiple options for generating reports about the selected content. It’s important to note that the term “report” can be multiple things within this feature. It might be a briefing document that provides an overview of a source. It can be a study guide, complete with quiz questions, answers, and a glossary of key terms.

It can also be a blog post or custom report that you design. It’s a pretty versatile tool that even offers suggested formats for you to start with. Teachers might use this to develop a study guide for their class, or perhaps to produce a report that summarizes survey results. Students could use this to help summarize content or develop a study guide of their own.

Number five: flashcards. This new feature is just what it sounds like. It’s a custom set of interactive flashcards based on the content that you have chosen. You can base them on one item in a collection, maybe a few custom-selected resources, or even the entire collection all at once. When you click the flashcard option, it will generate a set of cards. Simply click on the generated cards and you will see a series of flashcards with questions on them. Click to reveal the answer; it virtually flips over. Then click the arrow to move on to the next card.

Teachers could create a set of flashcards to use as a full class, or individual students could make their own flashcards for self-study on any topic or resource that they choose.

And number six: quiz. The quiz option is the final new feature of Notebook LM. This option generates a series of multiple-choice questions based on the content selected. Either click on an option that you think is correct, or click the hint button to get a hint. The hint button is a nice example of scaffolding built into the product.

If you click the wrong answer, you’ll get an explanation about why it’s incorrect, and you’ll also be shown the correct answer with an explanation of why that is the best answer. If you want more explanation, there’s an explain button that you can click to have AI generate a longer explanation of the concept and the correct response. Click next to move on to the next question.

Teachers could use this to get ideas for test or quiz questions, or they could use it for review with the full class. Students could generate their own quizzes for self-study.

Google’s Notebook LM continues to evolve. The new features—video overviews, mind maps, reports, flashcards, and quizzes—take this AI-powered tool to a new level. While the LM in Notebook LM technically stands for language model, I think if used right, it might be an abbreviation for “Learn More.”

To learn more about today’s episode and explore other free resources, visit AvidOpenAccess.org. Specifically, I encourage you to check out the article collection, “AI and the K-12 classroom.” And of course, be sure to join Rena Winston and me every 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.