AI-Powered Analysis & Insights
for Linked Notes, PKMs, and Knowledge Graphs

Use it to study and enhance your Obsidian, LogSeq, and RoamResearch data as well as Evernote, personal notes, etc.


InfraNodus applies advanced text network visualization to find the connections in your ideas and knowledge. It also reveals the gaps and patterns and then uses the GPT3 AI to help you generate new ideas to bridge those gaps.

 
Watch an Introduction
Visualize and Analyze Your PKM Knowledge Graphs

InfraNodus: Data Science for Your Thought

Visualize the data from your PKM vault or Evernote notes as a network graph. You can see both the [[backlink]] connections and automatically identified semantic connections between your ideas:


 
Obsidian knowledge graph analysis and visualization
 

InfraNodus graph visualization helps to detect the gaps in your ideas. We can then use the GPT based AI to help generate insight that will bridge those gaps.

1. Choose or Create
a Knowledge Graph

Import your Obsidian, RoamResearch, LogSeq graphs as the MD (markdown) files to InfraNodus, use our Evernote import app, or copy and paste.

2. Visualize the Relations
via Semantic Map

InfraNodus' text network mining algorithms will identify and present the relations between the concepts you use. If you use [[backlinks]], the connections between them will be shown too.

3. Generate Insights
and New Ideas

Once you know the structure, you can see the gaps in your ideas. Use GPT AI to generate facts and research questions to bridge those gaps and generate insight on top of your knowledge.



Multilingual

Use English, German, French, Russian, Spanish, Italian, Portugese, Swedish, Norwegian, Japanese, Chinese, etc.

Private & Exportable

All your data is private by default and you can export and download it any time in multiple formats.

Shareable in Hi-Res

You can link to your graphs, embed them to your website, and you can also download them in hi-res vector format.

Interactive Graphs

Use the network as a navigation tool through your knowledge. Explore every relation step by step, revealing its context.




Knowledge Graph Creation & Analysis Workflow

 

You can import Obsidian, RoamResearch, or LogSeq vault (MD files), import your Evernote notes, or input your text directly plain text or [[wiki-links]] using the built-in text editor and viewer.

Add the elements into the mindmap

See a graph of connections between your pages with powerful network science insights that help you identify the most important elements and the gaps in your knowledge.

Topic modeling and text mining using text network analysis

Switch to the concept view to view a semantic network of your second brain. You will see the most important topics and can link them inside the app.

Get the relevant excerpts using the graph

The graphs are interactive: you can remove the words to see what's hiding behind them. You can select them to see in which context they appear.

Structural holes in knowledge graphs generate new ideas

Use the built-in OpenAI's GPT AI to generate research questions and facts that can bridge the structural gaps in your ideas. Also an interesting way to let somebody else "play" your public graph.

Use OpenAI's GPT to generate research questions and innovative ideas for your discourse


Tutorial: AI-Generated Insights



What Else Can InfraNodus Do?

InfraNodus is not only a useful tool for building and analyzing your knowledge graphs. It is a powerful platform for text mining, sentiment analysis, social and discourse network analysis, and creative writing. Here are some other use cases you might like:


 

Use Case: Text Mining and Topic Modeling



Problem: What are the main topics inside a text?

The current solutions are either too simplistic or too technically challenging.


 
Solution: Topic modeling based on text network analysis and visualization.

InfraNodus will represent the text as a network and use powerful graph analysis algorithms to identify and visualize the main keywords, topics, and their relations.


Learn More    Try It Out

Use Case: Discourse Structure and Bias Analysis



Problem: How to identify the level of diversity and bias in a text or a network?

Suppose that we want to study the current discourse on coronavirus. What are the main topics and how diverse is the media coverage of this subject? What is the level of urgency?


 
Solution: Represent the text as a network and measure the diversity and bias of the graph structure.

InfraNodus represents any text as a network, so you can get insights about the structure of the discourse.

Based on the graph's modularity and distribution of influence across the different communities, we can measure the diversity of the discourse stucture and estimate its bias.

Watch the Video    Try It Out



 

Use Case: Creative Writing & Idea Generation



Problem: How to generate new ideas for your writing or at a brainstorming session?

Whether you are brainstorming, doing research or writing you may experience writer's block or simply get stuck for new ideas.


 
Solution: InfraNodus will represent your text as a network providing a visual overview and helping you find the gaps where the new ideas are hiding.

Our studies have shown that network representation of text encourages one to think in terms of connections, helping you make the new links between the different parts of your text and make your discourse more coherent.

You will also be able to see the structural gaps in your writing: that's where the new ideas our hiding.

Learn More    Try It Out

Use Case: Sentiment Analysis of Open Survey Customers Answers



Problem: Need to know what your customers think?

Open survey answers are hard to analyze. Positive / negative is not enough and tag clouds lose out the context.


 
Solution: Find the patterns in their open survey answers using network graphs.

With InfraNodus your customers' feedback will be visualized as a word graph where the words used in the same answer are connected.

This representation will reveal the patterns and context in your customers' answers, so you will see the main topics that appear in their feedback as well as the hidden relations between them that can't be uncovered by other tools.

Read the Case Study    Try It Out

 



 


See a Demo Graph     Create Your Own

 



 


Knowledge Graph Examples: Play a Second Brain

InfraNodus will also visualize a semantic network on top of your pages graph. You can switch this off, of course.

We took some existing publicly shared Obsidian / RoamResearch / LogSeq graphs and visualized them with InfraNodus.

We recommend to use the built-in GPT4 Insight AI to generate research questions or facts based on these graphs. It's very exciting, like playing with someone's brain while they are not there.

Accelerators and Venture Funds Mindmap
Hyperfine Village
Map
a RoamResearch graph by Lisa Hardy, 290 pages
Mind Map of Chinese Medicine
Fractal Networks Research
a LogSeq graph by Dmitry Paranyushkin, 79 pages
Graph nework visualization of news
Lorenz Duremdes' Second Brain
Obsidian graph of > 1800 pages, so takes longer to load, source: Github
Martin Luther King I have a dream text network visualization
Link Your Thinking (LYT) Graph
by Nick Milo, > 1200 pages so takes longer to load, source: LinkYouThinking

 
 
 
 

Start Using InfraNodus

Sign up for an account now, so you can get insight using this tool for your own data and texts.

How To Enhance Knowledge Graphs Using Text Networks

Most PKMs provide rudimentary graph visualization.

InfraNodus provides an interactive graph that can be used both to explore, to navigate, and to rewire your knowledge. Here's how it works:

1

1. Create or Import Your Knowledge Graph

You can create your knowledge graph from your writing, using InfraNodus as your PKM. It is also possible to import any data: from AI-generated text to your own PDF documents to Obsidian, RoamResearch, LogSeq or any other system's vaults (markdown files).

The text is converted into two networks that are shown at the same time: your backlinks and semantic relations in your text.

The algorithm representes every word as a node and every co-occurrence as a connection. If a concept is mentioned in a page, it is connected to that page on the graph. If the pages are mentioned in the same statement, they are also connected.

More in our Whitepaper
Create a Text Network Graph
2

2. Apply Network Science and Text Mining Insights

The network will then be generated from the text or data you added. The most influential nodes (concepts and pages) in the graph have the highest betweenness centrality and are shown bigger on the graph. The nodes (concepts and pages) that occur more often in the same context are aligned into topical clusters and have distinct colors.

Force-atlas algorithm is applied to create a special representation of those topical groups and influential hubs. Graph analytics is provided on every aspect of the graph's structure and individual nodes' properties.

Overview Data with Text Network Visualization
3

3. Generate Insight and New Ideas

InfraNodus will identify the structural gaps in the network: parts of the graph that could be connected but are not.

It will propose you the different ways how you can bridge these gaps to produce insight and generate new ideas. For example, by using the built-in GPT AI to come up with research questions and facts. Or using your own imagination based on the text ideogram presented to you.

You can also export your data as an MD file (augmented with InfraNodus insights) and import them back into your favorite PKM tools. Or use the built-in editor to build your ideas on top of the graph.

Generating Insight with Structural Gaps



Our Methodology in Detail

To learn more about the algorithms used in InfraNodus and for citations, please, refer to this peer-reviewed paper:

Paranyushkin, D (2019). InfraNodus: Generating Insight Using Text Network Analysis, Proceedings of WWW'19 The Web Conference, www.infranodus.com (ACM library, PDF).

If you want to know more about the algorithms used, here is the first paper we published on the subject:

Paranyushkin, D (2011). Identifying the pathways for meaning circulation using text network analysis, Nodus Labs. (Google scholar)


Become a Supporter!

InfraNodus is organic software and is developed without external funds or investors. We develop and maintain this tool and the associated research based on your contributions only. We believe it is a working model for crowdfunded software made by users for users.

You can support our work if you become a subscriber and get access to the cloud version or if you become our patron on Patreon. Enterpise, government, and educational versions are also available.

Pricing Options

This tool and the associated research in ecological network thinking are developed solely on the monthly contribution provided by users like you. We believe this is a working model for crowd-funded R&D, and we thank you for your support!

All quotas are per each text. There is no limitation on the number of texts you can process every month.

About InfraNodus: Our Philosophy

Gregory Bateson coined a beautiful term: "ecology of the mind". What is a mind that is ecological? It has the ability to have an overview, but it can also zoom into any idea. It embraces diversity, but it can also obsess over one thing when needed. It can discover the obvious, but it can also reveal the things that are hidden and ponder the gaps that have not yet been bridged. Rational and poetic.



InfraNodus is a tool that is developed to help you think this way. It is made to promote ecological dynamics and diversity on the cognitive level. InfraNodus visualizes and analyses ideas as a network, revealing the relations and patterns within them, so you can understand the dynamic complexity of how knowledge evolves and explore the nuances of meaning.

We believe that it is especially important today to make this kind of instrument available to everybody. That's why we develop InfraNodus so that it can be accessible to everyone, solely thanks to our users' monthly contributions and based on their feedback. This is not a start-up, in fact, it is more like the project of our lives. We don't have investors or an exit strategy. We are here to stay and to evolve.

We are constantly improving InfraNodus based on our users' feedback. We are also currently developing an API to make this way of thinking available to other applications and to enable the use of InfraNodus insights for machine learning and AI applications.

If you like our cause, please, sign up for an account and give it a try, support us on Patreon, or simply let us know that it resonates, because this is the best way to motivate each other.

Dmitry Paranyushkin, the founder

Cognitive Variability: Panarchic Thinking with InfraNodus


Panarchic thinking

 

 

 

Testimonials

InfraNodus is used by researchers, writers, marketing professionals and corporations. Here's what some of our supporters have to say: