Google used to literally have a feature for this! It was called Google Sets, back when Google Labs was still a thing.<p><a href="https://www.ghacks.net/wp-content/uploads/2009/08/google_labs-500x365.jpg" rel="nofollow">https://www.ghacks.net/wp-content/uploads/2009/08/google_lab...</a>
Google has the best autocomplete IMO, but below are some other search engine autocomplete endpoints if you want to explore.<p>DuckDuckGo:
<a href="https://duckduckgo.com/ac/?q=test" rel="nofollow">https://duckduckgo.com/ac/?q=test</a><p>Startpage:
<a href="https://www.startpage.com/do/suggest?limit=10&lang=english&format=json&query=test" rel="nofollow">https://www.startpage.com/do/suggest?limit=10&lang=english&f...</a><p>Qwant:
<a href="https://api.qwant.com/api/suggest?q=test" rel="nofollow">https://api.qwant.com/api/suggest?q=test</a>
What a beautiful way to map out the terrain - I immediately feel inspired to use this as a starting point for hobby-research projects. Only problem is now i'm inclined to check the alternatives to "ego graphs" as a starting point for research!<p>I have a sneaking suspicion that SEO/keyword mapping with all the resources devoted to that space may have some tools that elaborate on this idea - though im no expert. If anyone knows of useful tools to replicate this in browser I am all ears.
Neat idea, excellent presentation. What a brilliant write-up, I was thinking "I wonder how this works", and then I got to the detailed explanation of exactly how it works.
This is really useful! I've been exploring some Python data wrangling libraries / Pandas competitors (e.g. modin, Dask, Vaex, RAPIDS) and trying to find a nice way to visualise how they all 'link' together (similar to what Jake does in his "The Python Visualization Landscape" talk[0]).<p>The linked "Flourish" tool from the article is also really nice. It's a pity it doesn't have an API and is pretty pricey for the premium features, but the default network graph looks nicer than anything else I've seen.<p>I threw together a Repl here [1] (code at [2]) that lets you put in a keyword and produces CSV output that can be copy-pasted into Flourish (excuse the rough code)<p>[0] <a href="https://youtu.be/FytuB8nFHPQ?t=262" rel="nofollow">https://youtu.be/FytuB8nFHPQ?t=262</a><p>[1] <a href="https://google-vs-graphs.garethdwyer1.repl.run/" rel="nofollow">https://google-vs-graphs.garethdwyer1.repl.run/</a><p>[2] <a href="https://repl.it/@GarethDwyer1/google-vs-graphs" rel="nofollow">https://repl.it/@GarethDwyer1/google-vs-graphs</a>
Here’s an interactive version of this idea. <a href="https://anvaka.github.io/vs/?query=" rel="nofollow">https://anvaka.github.io/vs/?query=</a>
[Shameless plug] We have a scalable API for that! <a href="https://serpapi.com/google-autocomplete-api" rel="nofollow">https://serpapi.com/google-autocomplete-api</a>
First of all, this is an <i>incredibly</i> cool usage of autocomplete. Super-kudos to the author for finding something so conceptually simple to build, that results in data so rich and useful. (It also makes me miss the old Google Sets even more...)<p>But the results are <i>so</i> good, it actually gets me wondering if Google's autocomplete results for "vs" are actually just "dumb" statistical text mining from the web, or if Google has special code for when it sees "vs" to look up concepts in its own semantic/knowledge graph and generate the autocomplete out of those?<p>In other words, are these "ego graphs" distilling what is ultimately textual statistics from the web, or some kind of deep learning model Google has applied over that?<p>(Separately, I would <i>love</i> if someone could do this for the top million n-grams on the web and build a site out of it... I would visit it SO often.)
I don't believe the graphs that appear here. Trying it myself I obtain a very different thing. For example, from "matlab vs." the second completion is "octave", nowhere to be seen in tfa.
Can someone point me to resources on how to re-implement the "vs" feature?<p>I feel like this can be done with just GPT-2 instead of using the google search api. For example if you type something like "Instead of using Tensorflow, use ..." into <a href="https://talktotransformer.com/" rel="nofollow">https://talktotransformer.com/</a> it can babble pretty coherently about related technologies so the data is there.
Really cool idea! I didn't find the chess openings graph particularly useful, but what a fantastic way of finding related media! I'd love to generate clusters for my favorite movies, music, and games and use it for new recommendations.
I decided to try this with my last name, taking the ego graph concept literally. Along the way I discovered the existence of MMA fighter David Hošek and the Hošek-Wilkie model for sky coloration.
This is fantastic. It takes the idea of "vs" queries and adds a graph to glue together the various "vs" relationships. Props.<p>I only have one nitpick. The graph with dogs didn't include boxers (which everyone knows are the coolest dogs).