The 12 Days of AI: Day 7 – Conducting research

For Day 7 of The 12 Days of AI, the 20 minute task is to learn about AI-powered research tools.

To complete today’s task I need to use ResearchRabbit, an AI tool designed for efficient literature mapping based on citations, to help streamline my search for relevant references when embarking on an essay, small project, or literature review.

You know, whenever I need to do that type of stuff!

As noted on Day 7, “Here’s how it works: you initiate your search with one or more papers (referred to as seed papers). The tool then identifies and suggests additional papers related to the topic established by your seed papers. With ResearchRabbit, there’s no need to toggle between different search modes and databases, eliminating the tedious and time-consuming citation mining process. The name ‘ResearchRabbit’ was inspired by the desire to avoid these daunting and often overwhelming rabbit holes of research”.

Going down the ResearchRabbit hole

I ignored the instructions for Day 7 and followed along with the how to use ResearchRabbit video instead, which resulted in a nice outcome on published papers from the Monash Mindfulness MOOCs which I led from 2015 to 2020. Nice.

Here’s my experience of using ResearchRabbit to explore published papers relating to monash mindfulness and related topics, which I captured as screenshots.

Reflecting on the Day 7 task

Was the task useful? Absolutely, it was. Developing an understanding of new tools that make your production/research more efficient is always useful.

Would this be a useful tool for conducting your own research or professional practice? Of course, especially with the labour-intensive task of traversing through all of published papers/articles and making the cognitive connections – of course there’s still a human element of deciding its usefulness or not but the grind of finding stuff has been diminished, which is great.

What did I like about the layout and its ability to find other related articles? The layout was intuitive and the way your exploration of the going further down the rabbit hole was displayed from left to right, really worked well for me.

Can you see any potential limitations? Potential limitations could be any bias or constraints of the AI tool (currency of papers and papers behind paywalls etc) or even limitations of the user, that is, a reliance on the tool to do the labour. Yes, using the AI tool is probably more efficient but there is some skill in parsing content and analysing for use etc.

Research Rabbit doesn’t explain how its algorithms work – does this matter? Yes, and no, or even, maybe.

If a student asked you could they use it to do and assignment for you – what would be your response? Yes, as long as they understand that they cannot rely solely on the tool and that there may be other options or approaches worth considering, especially when it comes to articles or papers behind paywalls because ResearchRabbit may only rely on publicly accessible materials – unsure because ResearchRabbit doesn’t reveal how it all works.