Day 66 of #100daysofnetworks
GrooveSeeker: Mapping Music and Art Collaborations
Hi everybody!
Something really cool happened today, so I want to write about it! Today is going to be another spontaneous article, which feels much more like the original series.
I recently had a conversation on LinkedIn about GrooveSeeker, as I was doing a fun LIMITED EDITION sticker giveaway!
These are some cool stickers, and we did a promotion!
Cool, cool stickers. I’m really happy with how Verdant Intelligence and GrooveSeeker are both doing, and I’m excited for what we are planning in February.
Anyway, I was having a conversation, and we were discussing how GrooveSeeker data could be useful for:
Finding artists who are like your favorite artists
Finding artists who are possibly similar based on collaborations
For instance, punk rock bands are similar to other punk rock bands. They are not identical, but they have similarities.
And bands that tour with Green Day might also be similar to other bands that tour with Green Day.
Collaboration Networks
Then I remembered, we have already done an article on musical collaboration networks!
I wrote that article in 2023, two years ago, using music collaboration data that I pulled from Spotify. That was really fun analysis, and the insights were interesting! Read the article and you’ll see.
But then I realized that I could do something much cooler with my own company’s data!
From that idea, I quickly built a new product today! I now have an active feed of musical and artistic collaborations! Neat!
In this network, if two music acts (Green Day and Chris Stapleton) are linked together, it’s because they participated in the same event. They collaborated on the success of an event, not in the creation of an album or a song.
From this image, it is pretty obvious that Green Day is mainstream as it is linked to Electronic Music.
If I search on GrooveSeeker, I can see what’s going on:
Neat. This has to do with events surrounding the Super Bowl.
You can access GrooveSeeker at gsv3.ai. You can search your city, favorite genres, favorite bands, etc. It is easy to use, and has live data. You should use it!
Explore and Have Fun!
Because of this random creative brainstorming session on LinkedIn, I was reminded of something I did in 2023, and I created a new product! I will talk more about its usefulness as a product another time, but JUST GO HAVE FUN!!!!
Click Me! Check out Music and Art Collaborations!
If that link doesn’t work, copy and paste from this textbox.
https://cosmograph.app/run/?data=https://raw.githubusercontent.com/itsgorain/100daysofnetworks/refs/heads/main/data/gsv3/gsv3_entity_collaboration.csv&source=source&target=target&gravity=0.25&repulsion=1&repulsionTheta=1.15&linkSpring=1&linkDistance=10&friction=0.85&renderLabels=true&renderHoveredLabel=true&renderLinks=true&nodeSizeScale=1&linkWidthScale=1&linkArrowsSizeScale=1&nodeSize=size-total%20links&nodeColor=color-default&linkWidth=width-default&linkColor=color-default&After clicking it, there will be a few seconds of delay and then you should see something like this:
It won’t be exactly this, but it should be similar. The major nodes will start to identify themselves.
You can use your mouse wheel to zoom in and out.
More interestingly, look for the Info tab on the top left. Click it.
Then look all the way at the bottom and search for groups that you know about and/or enjoy.
I see that Galantis is actually three nodes. Good to know. If I click on the first one, and then click “Open Table” right above it, I can see what happened on what dates.
Nice. Looks good!
Ok, at this point, I don’t want to keep guiding you, showing you what to do. I really want you to try things, click buttons, move sliders left and right, tinker with the networks. Explore them. You learn a lot through exploration.
Click Me! Check out Music and Art Collaborations!
I hope you enjoy the feeling of exploring a music and art collaboration network. This is really neat. I have so many ideas for this already.
This is just so cool. That is all for today! I really hope you will click the link and play with the graph!
Please Support this Work!
I have written over 60 articles for this series. Each one takes about four hours of research, and several pages of writing and editing. Here are some ways you can support the blog!
Please mention this blog to your friends and colleagues.
Please subscribe if you have not. This motivates me like nothing else!
BIGGEST HELP to the BLOG: Please consider upgrading if you are a subscriber. Thank you to all current paying subscribers for making this research and development possible! You can have Database access and minimal GraphRAG code if you want it.
Please buy my book to understand how I think about Natural Language Processing and Network Science combined.
I will open up early access to my second book Graph: Zero to Hero very soon. Please stay tuned.
Platform access to the Living Library of Knowledge is opening, NOW. Please let me know if you are interested in access.
Please reach out to me if interested in training related to Data Science, Data Engineering, Network Science, Knowledge Graphs, Artificial Intelligence, or anything else I write about. Feel free to message me on Substack or on LinkedIn!
Feel free to hang out in the comments and have a good time!
We have come so far since the very first day of the very first #100daysofnetworks. I love writing for this series. Thank you for being a part of it!
“I really want you to try things, click buttons, move sliders left and right, tinker with the networks. Explore them. You learn a lot through exploration.”
i always really appreciate this kind of mindset. you get people knowledge, show them something neat, and let them tinker. it really helps lock in knowledge.
great stuff!
Grooveseeker is much faster than I thought it would be. It's a great tool!
If your willing to take suggestions, I have two.
1. If a link leads to a paywall site, can you indicate it somewhere near the external hypertext link so the user knows before clicking it?
2. As the user types in the search box on the left side and the results start loading on the right side, could you have the typed (as well as when typing) letters be highlighted within the results? Sometimes a band is part of a concert and all of the artists for that concert get scraped into the same results box. It would be a nice feature if the user could see what they typed (or are still typing) highlighted within results containers.
I hope this makes sense!