Day 46 of #100daysofnetworks

Blog "Series", Bluesky Crawling, Specialized Training, and More!

Welcome to another day! Today, I have some exciting updates about #100daysofnetworks. I’m adding some new features and ways to learn, and I’m excited to share some of my own learning that I have been doing.

Bluesky Crawling!

First, I have been working on promoting this blog on other platforms. Part of that work involves researching what other platforms I could be using, and whether they have a way for me to understand the platform itself.

I realized that Bluesky has a very easy API to work with, and this is useful for my own infiltration of the network. I want to become a part of the data science and network science communities over there, so:

• I used the API to find other people like me

• I followed them

• They followed me back

• We now interact

That’s how infiltration of social media can be done. That’s how you extend your reach.

So, I did some of that this week, and if you or your business would like to learn how to do this, please let me know. This is important for being able to promote your ideas and products. If you aren’t in a position to be seen, you will not be seen.

In 2018 or so, I learned how to crawl Twitter, and that spawned the original #100daysofnetworks. Learning to crawl Bluesky is going to have similar big impact, because there has been a gap since Twitter massively increased their prices.

That means, you can use Bluesky for sentiment analysis and other kinds of research you used to do on Twitter. Do it on Bluesky, for free.

I can teach you, but not for free. I am thinking about spinning up a side series and charging $200 a person to learn how to do this. That is cheap tech training. Any interest?

This is a powerful skill that you should have in this age of intelligence. This is crawled Bluesky data.

AI Engineering Meets Network Science

Next, I have come up with a new strategy for how I will be writing these articles, as there will be much more close work with Artificial Intelligence. So, from now on, this blog will be a bit split brained.

Brain 1: Artificial Intelligence, Prompt Engineering, Agentic Stuff, etc

Brain 2: Network Science, Graph Theory, Social Network Analysis, etc

I use Brain 1 when I need to do things with AI. For instance, I used GPT 5 to create edgelists from the stories of Alice in Wonderland and Through the Looking Glass and included them with the code that supplements today’s post.

Later, we will use Brain 2 to analyze that data and do some validation work. Validation work falls under Brain 1, but we’ll incorporate it into Brain 2 work so that it becomes fluid.

Since I am now doing much more with the AI Engineering side, I will be explaining that a lot more. I will be writing a lot more about AI engineering, and have been all week. I did that in the previous article.

New Series, or Streams, or Whatever!

I have been doing some analysis of my blog itself. I downloaded all 45 of the articles I previously wrote and used GPT 5 to identify the subtopics that I talk about.

Analyzing the outputs, you can see what I spend most time writing about.

That makes sense. I wrote my book out of frustration over Graph Visualization, so it is understandable that I spend a lot of time talking about this.

If we use Bipartite projection and map this out, this has shape.

Just for fun, I had AI draw this. Let’s see how it compares, for accuracy.

GPT 5 dropped a node. In the top right, Whole Network Analysis fell off. So, don’t blindly trust AI to do things. You have to validate the outputs, and I will later write about some of my strategies for doing so. Still, cool picture, but it shows that real intelligence and know-how is superior to current AI. Learn skills.

If we do Bipartite Projection on the day instead, it looks like this:

That is not super useful for anything other than it shows the interconnectedness of these topics. There are many topics involved in Network Science. There is a lot to learn and fall in love with, and this is not common knowledge.

But even as complex as this is, you can explore individual topics, and I will make that much easier to do in coming days.

If you wanted to read what I wrote about Artificial Life, you can read days 19, 27, 28, 29, and 40.

Community Detection is covered on many more days than Artificial Life. There is more to read and learn from. But it also means that I could explore Artificial Life more, and write more about it.

And so far, I have written about Attack Simulation on days 4, 13, 22, 23, and 24.

Look at the clumps of days, also, for clues. This means that I was really interested in writing about Attack Simulation around days 22-24, and that I touched upon it before. Learn to read human signals at a glance. Learn to parse human signals from graph visualizations.

On the 100daysofnetworks blog itself, I will create a new page, called Series, or Sessions, or Specializations, or something. Leave a comment with your idea, if you have one. The point is I will give people a way to zoom in on what they are most interested in. For instance, Cybersecurity people need to understand Attack Simulation, but Computational Linguists probably do not.

Alice Datasets

In today’s code, I also link to several Alice datasets that I am providing. Use them. Play with them. Analyze the data. Validate how well the GPT models did the job. Do stuff. I am giving you stuff for free. Learn with it.

This kind of data doesn’t just happen. This is the output of my AI Engineering. With these datasets, you can:

• Learn Network Science. Source and Target are your edgelist. This is relational data.

• Learn Natural Language Processing. This is language data.

• Learn AI engineering. Validate the work the AI models did. What did GPT4 miss that GPT5 caught? What reasoning did GPT5 do better than GPT4? Did GPT4 do anything better than GPT5?

This is incredibly valuable but only if you use it. You are sitting on potential, but that potential doesn’t become anything by sitting on it or simply knowing about it. You have to use it.

While you learn, I will work on getting this blog better organized. While I do that, please help me by telling your friends about this place or by subscribing. Help me help you.

Get today’s code and data.

That’s all for today! Check out the code and analysis. Learn from the outputs. Try things and learn new skills!

Need Any Help?

Finally… there’s no fun way to say this. I am out of a job and need to find work. If you work in Data Operations, Data Engineering, Cybersecurity, Data Science, or do anything with Artificial Intelligence or Machine Learning and you think I can be of use to your company, please reach out.

I need full-time work with benefits. I need a good problem to help solve. I enjoy collaborations, but I need to pay mortgage and expenses. I am very good at what I do, and I am very good at making companies more effective. I’m a very friendly person and a good teammate, so let me know if you think of anything. Or pitch in and buy a coffee to support this writing.

Please Support this Blog

I would like to make a special request in this article. This blog has over 600 subscribers. I have written over 40 articles. Each article typically involves about four hours of research and development, so that’s about 200 hours of valuable work and writing that I’ve provided for free, because most important is that I want people to learn this. I am not doing this to make money.

However, these days, there are things that I would like to do. For instance, to play with GraphRAG for AI, it is useful to have access to a Graph Database. The cheapest tier Neo4j instance is about $800/year. I would like to work on GraphRAG and write about it so that you all learn, but I cannot do that without support.

So, I have opened up a few ways for you to support this blog:

• If you are a subscriber, please consider converting to a paid subscriber. I provide code, data files, and coding explanations that are absolutely worth more than $8 per month. But I understand that not everyone can afford to pay, and that’s fine. Free is absolutely fine, for those who need free.

• If you are a paid or unpaid subscriber and you want more flexibility in your contributions, I set up a ko-fi account. CLICK HERE. You can use this to buy me a coffee ($5 donation) or even to pitch in for a Neo4j Aura instance, which will enable more writing and learning.

• And no matter what, if you are here, please buy and read my book. I am working on more book projects, as mentioned on Day 43.

Oh, and please participate in comments. I am a friendly guy. It is lonely in the comments and always weird to me that people don’t seem to want to talk about this stuff. Why not? What is on your mind? Have any cool ideas you want to brainstorm? Don’t be intimidated, for sure. Be creative instead.