I have been playing around with Google’s Notebook LM. One feature is the audio overview option. This produces a podcast-type audio discussion that reviews the documents that you ask it to. For this podcast, I asked it to do this for my paper, More than Just Food, which I published in 2019. I was really impressed with the outcome. The podcast lasts about 16 minutes. Have a listen. What do you think?
Category Archives: Research
Narrating the power of food clubs with AI
In a previous post, I talked about using Gemini to explore the impact of my research. Today, I am going to explore that research with a different tool: Notebook LM. The big difference between Gemini and Notebook LM is that Gemini searches the web, and as I found, not always so successfully, while Notebook LM looks just at what you ask it to.
So I did an experiment. I put the same paper I used for the Gemini experiment, a report I am working on right now (to be released soon, so watch this space), the recently published UK national food strategy, some recent research on Food Banks by the Trussell Trust, and a link to the food ladders discussion in this blog. One of the features of Notebook LM is that it can produce a video summary of the things you ask it to look at and present it in a narrated slide show. Here is what it produced. What do you think?
At present, you don’t have the option to change the accent (sorry, and that is not me). I think it does quite a good job of juggling across a number of quite dense sources. If you want to digest things quickly, it’s a good option. There are some nuances that are missing, but this seems reasonable for a 6-minute video. What is missing from this is what happens at rung three, and where we go once we leave the food club? I’m not sure we’ve cracked that one yet.
If you want a deeper dive, Google’s Notebook LM also allows you to ask for an audio overview that lasts about 20 minutes. It does this in a rather entertaining interview style. It is worth trying out. You still need to read the documents to get the nuance, though.
Using AI to understand the influence of research
I have become a fan of Google’s AI tools. They are fantastic for summarising and revising text to make it clear, concise and well-formed. There are some limitations, of course. Gemini, for example, can make up sources, and it cannot access everything that one might think of as being ‘open access’. Notebook LM is great for cutting across articles and notes that the user feeds directly into the notebook. This helps bypass the making things up element. While Gemini seems to be better at producing concise text, Notebook LM can be a bit verbose; both have their uses.
I thought I would try an experiment with a paper that I am very familiar with because I wrote it. I wanted to see what sort of results I could get from Gemini on the influence or impact of the paper. The paper that I was exploring was my 2019 paper, “More than Just Food: Food Insecurity and Resilient Place Making through Community Self-Organising,” published in Sustainability (https://www.mdpi.com/2071-1050/11/10/2942).
Gemini’s process
Using the deep research function, I asked Gemini, “How has this paper been used by other researchers to shape their research?” and included a link to the paper. The benefits of the deep research function are that it tells you what the thinking process is and then produces a report based on what it finds. The PDF linked shows all the ‘thinking’ Gemini did to arrive at a final report. A few immediate observations about this. Firstly, Gemini does an excellent job cutting to the key contributions of the paper. Secondly, I knew pretty much where to look, but it encountered access problems, which are likely to limit the ability of Gemini to provide clear and meaningful answers to prompts that students or other researchers may have about a particular research topic. Thirdly, Gemini does try to find workarounds that seem plausible; however, again, it encountered access problems.
Gemini research steps for determining the impact of Blake (2019), More than Just Food – Google DocsDownload
The report it produces
This is the report that it produces from its somewhat limited ability to access citing literature, despite this literature being mostly open access. The first interaction did not include the (somewhat difficult to read) table at the end, but when I pointed this out, the table was added. You have the option to export the report as a Google Doc, which is really handy. What the report doesn’t do is what I wanted it to do, which was a review of all the papers that cited my paper. It does show where the contributions of the paper to the literature are, but not specifically how my work is being used. However, it is still nice to have a clear summary of not just what the contribution is, but also how it is a contribution. It is also really positive, which is a bit of an ego boost.
Shaping the Discourse_ The Enduring Influence of Blake (2019) on Food Insecurity and Community Resilience Research – Google DocsDownload
This summary of my research also tells me some other things about my own research. Given the number of contributions that it finds to a whole range of areas–something that is inherently a problem linked to my Dyslexic mind, as for me it is all interconnected. I clearly need to work on limiting the ways that I seek to make my research publications relevant by focusing on making one or maybe two contributions if I want others to use the work in their research. Too many contributions make it hard for others to see what is most important and then use that centrally in their own work.
AI for Research: A Realistic Look
My experiment with Gemini AI offered a fascinating look into how these tools gather and present information, revealing both their strengths and their current limitations when it comes to assessing a paper’s impact.
It clearly shows that AI tools, like Gemini, excel at providing quick summaries and pinpointing a paper’s main arguments, giving you a valuable head start in understanding its essence. AI can also help you understand a paper’s broader thematic contributions – how its central ideas resonate and are adopted in wider academic discussions. This encourages a more conceptual way of thinking about how research influences a field, moving beyond simply counting citations.
However, these tools are not perfect. It’s crucial to always cross-reference information, be aware of potential ‘hallucinations’ (where the AI invents facts or sources), and recognise that AI may not have access to all relevant literature, even if it’s publicly available. While AI is a powerful tool, it doesn’t replace the need for researchers to master traditional, comprehensive literature search strategies. Interestingly, observing Gemini’s ‘thought process’ can even offer students a blueprint for developing their own effective search strategies using academic databases like Google Scholar, Web of Science, or Scopus. This combination ensures both thoroughness and accuracy in your research.
Finally, using AI like Gemini can help you refine a paper’s core contribution. By summarising its perceived impact, it can highlight if a paper’s scope is too broad or if it attempts to make too many distinct contributions. For greater impact and easier adoption by other researchers, focusing on one or two central, clearly articulated contributions per publication can make your work more digestible. You can even use AI prompts to help revise your writing for better focus. It might also reveal thematic connections you hadn’t considered, sparking new ideas for future research.
Ultra Processed Food, Stomach Share, and the Problem of Food Contexts
Ultra processed foods are in the news more and more. A recent meta-study found there are a myriad of health issues linked to diets comprised primarily of such foods. When thinking about the level of processing, foods are typically categorised into 4 groups: unprocessed or minimally processed, processed culinary ingredients, processed foods and ultra-processed foods.
Processing is not a bad thing in and of itself. Pickling, fermenting, canning, even chopping and cooking are processes. We process things to turn them into food at home, in restaurants and in factories. Ultra-processed foods are distinctive in that they change the nature of the original ingredients, such that very little of the original whole food is left, and they include chemicals that you would not find in an ordinary kitchen. These include emulsifiers, artificial colours and flavours, stabilisers, sweeteners, and other additives to make them taste better and last longer. They also are fatty, salty or sugary and lack dietary fibre. What we might think of as empty calories.
Ultra-processed foods are also less expensive and, because they last longer than fresh foods, are less risky for a tight household budget. But we pay for this low cost in other ways. Individually, we pay for this food with our health. We also pay collectively, if somewhat unevenly, for it with the environment. Ultra-processed foods drive mono-crop production that undermines ecosystems and harms biodiversity. The processing is also energy-intensive and dependent upon petrochemical inputs, thereby contributing to climate change.
We can tell people to stop eating these foods, but educational campaigns won’t work on their own. People need to have the capability to eat differently. If those foods that are better for you are not available in the place where you live or they are too expensive then all that the education will do is create further feelings of guilt.
Ultra-processed foods are a key part of a system that rewards producers for creating these foods in the form of profits now, whilst undermining our global food security now and into the future. Because this is a systemic problem we need systems solutions that intersect at all points of the supply chain and operate at different scales. Introducing disincentives for the production and sale of ultra-processed foods, shifting to agroecologiecal farming practices, and re-introducing these better foods into neighbourhoods all need to be considered.
I recently participated in a webinar by Healthy Diets Healthy Life (HDHL) as part of the European Commission’s Bioeconomy Changemakers festival. In addition to learning about HDHL and hearing two other speakers talk about ultra-processed foods from a bio-economy and a nutrition perspective, I talk about the contexts within which people access and purchase food. My section starts at about 38 minutes in.
So what can we do right now? We can pressure government to put constraints on the way those in the food sector operate and provide incentives to act in a way that is better for both health and the environment. Individually, we can also try where we can to introduce more foods into our diets that replace the ultra-processed foods we currently eat. As a society, including commercial organisations, we can also support initiatives that help people by expanding their access to and knowledge of those foods that are better for them, which do so in non-stigmatising ways. I talk about two such initiatives in the video.
GeoFoodie 
You must be logged in to post a comment.