graph view:
×  ⁝⁝ 
Graph Language Processing Settings:

Specify the settings for your text-to-network conversion algorithm for this graph.
Lemmatizer: ?
Every word will be converted to its lemma (e.g. bricks > brick, taken > take) and will be shown on the graph as a node. Set to your language for more precise results. Switch off to turn off lemmatization and add your custom stop words list below.
Show on Graph:   Double Brackets [[]]:  Categories and Tags:   
Stop Words: ?
List the words, comma-separated (no spaces), that should not appear in the graph, in addition to your default global stopwords list.
Example: is,the,as,to,in

Synonym Nodes: ? unmerge all
If you'd like some words to appear as one node on the graph, in addition to your default global synonyms list, list the synonyms, one per line.
machine:machine learning
learning:machine learning


×  ⁝⁝ 
Dynamic Graph Settings

See the dynamic evolution of this graph: scroll or "play" the text entries to see how the text propagated through the network graph over time.

the final graph

highlight propagation edge
show visible statements only

Play the Graph

current speed of the player:
0 2000

one statement at a time

×  ⁝⁝ 
Export the Data

Network Graph Images:

The graph images for publishing on the web or in a journal. For embeds and URLs use the share menu.
PNG (Image)  SVG (Hi-Res)

Visible Statements (Tagged):

Export the currently filtered (visible) statements with all the meta-data tags (topics, sentiment).
CSV (Spreadsheet)   MD (e.g.Obsidian)  

Network Graph Data:

The raw data with all the statistics for further analysis in another software.
JSON  CSV  Gexf (Gephi)

All the Text:

Plain text used to create this graph without any meta-data.
Download Plain Text (All Statements)
× ⁝⁝ 
Share Graph Image

Share a non-interactive image of the graph only, no text:
Download Image Tweet
Share Interactive Text Graph


×  ⁝⁝ 
Save This Graph View:


×  ⁝⁝ 
Delete This Graph:


×  ⁝⁝ 
Project Notes:
Top keywords (global influence):
Top topics (local contexts):
Explore the main topics and terms outlined above or see them in the excerpts from this text below.
See the relevant data in context: click here to show the excerpts from this text that contain these topics below.
Tip: use the form below to save the most relevant keywords for this search query. Or start writing your content and see how it relates to the existing search queries and results.
Tip: here are the keyword queries that people search for but don't actually find in the search results.

I recently went through the process of renewing my driving license, which made me think of two important components of our future infrastructure. One is the Oracle problem in blockchains, how to connect external data sources to the consensus mechanisms that blockchains offer. Second, obviously, weather this would be the last time that I needed to renew my license, because with the hopeful, rapid deployment of self driving cars, I wouldn't need to drive myself again. My name is David Orban. And this is the context the driving licence is a good piece of evidence of a skill that you must exhibit in order to get access to a certain set of benefits. In this case, the ability to sit in the driver's seat of the car and go wherever you want. It has been developed in order to regulate a very dangerous activity. More than a million people die in car accidents all over the world, every year. And this is already under the regulated environment where the possession of a driver's license should be

   edit   deselect   + to AI


an indicator of the ability to perform the task to an expected level a which evidently doesn't happen. Now, the performance issue aside the process of achieving managing renewing as in my case, the certificate itself, the driving license, varies across the world, from country to country, but everywhere, as of today, it is a centralized mechanism where you obtain a piece of paper or plastic more frequently today, hopefully, which shouldn't be for jable should give the bearer and anyone wanting to check it sufficient confidence in its authenticity and information of for example, not only the ability to detect the degree I for example, and not licensed to drive a large truck. Now, as in every other certificate, there are a lot of advantages in reforming the system that is now in place and bringing it into a more modern architecture where the certificate itself would be harder to forge verifying it would be more secure and definitive. updating it with additional skills would be fast and

   edit   deselect   + to AI


reliable. And many many other points that actually are satisfied by a blockchain implementation of this particular certificate, the driving license and many others as well. An important only partially solved problem is what in the blockchain world is called the Oracle problem. How do you bring into the self contained world of provable truths, that is blockchain with its consensus mechanism, being able to prove a computable statement and say that it is for every possible effect through a piece of data from the outside world, from the world of messy information of uncertain reliability

   edit   deselect   + to AI


or even wear people actively try to inject false information into systems in order to gain an unfair advantage. More classically, this is termed as garbage in, garbage out. If you cannot trust the source data, you cannot trust the computing performed upon the data and the results of that computation. So, the blockchain Oracle problem is not new, or completely new, but it is especially acute in this pristine isolated system that aims to be on a pedestal of trustworthiness to a much higher degree than not any other previous solution. In my case, I went to do a relatively superficial medical exam, concentrated mostly on my eyesight. And yes, I have been already under the obligation of wearing glasses while driving. And of course, that has been kept. My eyesight did not deteriorate further. So my relation is fine. And yes, I was confirmed that I'm able to drive. There can be many other ways and many other reasons to either confirm or deny a certification and an ability. But then after the

   edit   deselect   + to AI


person to person interaction of this particular exam, the data that is being processed is, you know, ambiguous, it travels on all kinds of analog and not especially trustworthy digital networks. Until Well, it enters the current system. And I don't know how many false driver's licenses are circulating. Today, what is the percentage whether it is single digit percentage or double digit percentage, but yes, once the data is in the system, today, it is assumed to be trustworthy or easily verifiable. So the objective of extending the trustworthiness of the beta, broad onto blockchain based systems that will be able to hold and manage and enable the verification of certificates all over the world is pretty important. The extension of this trustworthiness requires a careful balance of were to include blockchain, which is necessarily inefficient, because of the effort that it takes to arrive to the decentralized consensus it requires and where to take in important shortcuts. What do these

   edit   deselect   + to AI


shortcuts entail? Where does the human component enter into the picture? And is the human component an acceptable vulnerability of the entire system? Humans are often flexible, and they are able to question the rules and the reasons why certain things are done. So in this sense, including them in processes can be absolutely crucial.

   edit   deselect   + to AI


But on the other hand, humans make many many mistakes as well. The million Car accidents per year, leading to loss of human life, in the vast majority are caused by human mistakes. So I believe that the next challenge for blockchain systems will be the careful understanding and balancing dynamically of these boundaries, where can automated systems extend themselves, and where does the error prone but flexible and self reflecting human judgment enter the picture. This is the conjunction with self driving cars. Because it is believed that the diffusion of self driving cars will radically reduce the rate of fatalities and the rate of accidents. But in the meantime, while we are getting there, there has to be a strong interaction between the human systems and the autonomous machine systems that self driving cars represent. For example, this interaction today is in not only the ability, but the requirement that a human driver sitting in the driver's seat could take over must be able to

   edit   deselect   + to AI


take over the driving of the of the car in a situation where the car cannot make the right choices. under the assumption that, yes, the human will make a better choice in time. And this is extremely delicate, because we tend to be distracted already when we concentrate on the task, let alone when we are told that we are allowed to be distracted, except that we must pay attention and be ready to take over. It is a little bit of a paradox. I am very much looking forward to self driving cars, I fully believe that they will be able to deliver the promised benefits, and that the transition will be delicate, but fairly rapid over the course of a few years. It will be firmly established that self driving cars are trustworthy, and they are desirable to be deployed in ever wider waves, it will take a much longer time to replace the current fleet, the cars on the roads and trucks and all other transportation to be able to drive themselves. And some will keep a human component for a much longer

   edit   deselect   + to AI


time than others. I personally feel that it is likely this was the last time for me to renew my driver's license next time after the license expires, and I want to drive and I will do it in a closed circuit. And I will maybe drive a race car and it will be risky. And I will have a special insurance paying a high premium just for that hour or so of entertainment. But as far as moving around my ability to reach my destination and safely and securely and on time will be delegated to the machines. And of course these machines and their abilities will be also

   edit   deselect   + to AI


checked and verified and certified and certifiable on blockchains with Oracle's bringing the data from the outside world onto the blockchain in a much more reliable way, with machine to machine communication, updating on a real time basis. The fact that self driving cars are actually great than not any human based Oracle's are doing today certifying our own ability to drive cars.

   edit   deselect   + to AI


× ⁝⁝ 
Show Nodes with Degree > 0:

0 0

Total Nodes Shown:

Filter Graphs:

Filter Time Range
from: 0
to: 0

Recalculate Metrics Reset Filters
Show Labels for Nodes > 0 size:

0 0

Default Label Size: 0

0 20

Edges Type:

Layout Type:


Reset to Default
semantic variability:
×  ⁝⁝ 
×  ⁝⁝ 
Semantic Variability Score
— modulates diversity of the discourse network  how it works?
The score is calculated based on how modular the structure of the graph is (> 0.4 means the clusters are distinct and separate from one another = multiple perspectives). It also takes into account how the most influential nodes are dispersed among those clusters (higher % = lower concentration of power in a particular cluster).
Actionable Insight:


We distinguish 4 states of variability in your discourse. We recommend that a well-formed discourse should go through every stage during its evolution (in several iterations).

  1 - (bottom left quadrant) — biased — low variability, low diversity, one central idea (genesis and introduction stage).
  2 - (top right) - focused - medium variability and diversity, several concepts form a cluster (coherent communication stage).
  3 - (bottom right) - diversified — there are several distinct clusters of main ideas present in text, which interact on the global level but maintain specificity (optimization and reflection stage).
  4 - (left top) — dispersed — very high variability — there are disjointed bits and pieces of unrelated ideas, which can be used to construct new ideas (creative reformulation stage).

Read more in the cognitive variability help article.
Generate AI Suggestions
Your Workflow Variability:
Shows to what extent you explored all the different states of the graph, from uniform and regular to fractal and complex. Read more in the cognitive variability help article.

You can increase the score by adding content into the graph (your own and AI-generated), as well as removing the nodes from the graph to reveal latent topics and hidden patterns.
Phases to Explore:
AI Suggestions  
×  ⁝⁝ 
Main Topical Clusters:

please, add your data to display the stats...
+     full table   ?     Show Categories

The topical clusters are comprised of the nodes (words) that tend to co-occur together in the same context (next to each other).

We use a combination of clustering and graph community detection algorithm (Blondel et al based on Louvain) to identify the groups of nodes are more densely connected together than with the rest of the network. They are aligned closer to each other on the graph using the Force Atlas algorithm (Jacomy et al) and are given a distinct color.
Most Influential Elements:
please, add your data to display the stats...
+     Reveal Non-obvious   ?

AI Paraphrase Graph

We use the Jenks elbow cutoff algorithm to select the top prominent nodes that have significantly higher influence than the rest.

Click the Reveal Non-obvious button to remove the most influential words (or the ones you select) from the graph, to see what terms are hiding behind them.

The most influential nodes are either the ones with the highest betweenness centrality — appearing most often on the shortest path between any two randomly chosen nodes (i.e. linking the different distinct communities) — or the ones with the highest degree.
Network Structure:
The network structure indicates the level of its diversity. It is based on the modularity measure (>0.4 for medium, >0.65 for high modularity, measured with Louvain (Blondel et al 2008) community detection algorithm) in combination with the measure of influence distribution (the entropy of the top nodes' distribution among the top clusters), as well as the the percentage of nodes in the top community.

Reset Graph   Export: Show Options
Action Advice:
Structural Gap
(ask a research question that would link these two topics):
Reveal the Gap   ?   Generate an AI Question
A structural gap shows the two distinct communities (clusters of words) in this graph that are important, but not yet connected. That's where the new potential and innovative ideas may reside.

This measure is based on a combination of the graph's connectivity and community structure, selecting the groups of nodes that would either make the graph more connected if it's too dispersed or that would help maintain diversity if it's too connected.

Latent Topical Brokers
(less visible terms that link important topics):

These are the latent brokers between the topics: the nodes that have an unusually high rate of influence (betweenness centrality) to their freqency — meaning they may appear not as often as the most influential nodes but they are important narrative shifting points.

These are usually brokers between different clusters / communities of nodes, playing not easily noticed and yet important role in this network, like the "grey cardinals" of sorts.

Emerging Keywords

Evolution of Topics
(number of occurrences per text segment) ?
The chart shows how the main topics and the most influential keywords evolved over time. X-axis: time period (split into 10% blocks). Y-axis: cumulative number of occurrences.

Drag the slider to see how the narrative evolved over time. Select the checkbox to recalculate the metrics at every step (slower, but more precise).

Main Topics
(according to Latent Dirichlet Allocation):

LDA stands for Latent Dirichlet Allocation — it is a topic modelling algorithm based on calculating the maximum probability of the terms' co-occurrence in a particular text or a corpus.

We provide this data for you to be able to estimate the precision of the default InfraNodus topic modeling method based on text network analysis.
Most Influential Words
(main topics and words according to LDA):

We provide LDA stats for comparison purposes only. It works with English-language texts at the moment. More languages are coming soon, subscribe @noduslabs to be informed.

Sentiment Analysis

positive: | negative: | neutral:
reset filter    ?  

We analyze the sentiment of each statement to see whether it's positive, negative, or neutral. You can filter the statements by sentiment (clicking above) and see what kind of topics correlate with every mood.

The approach is based on AFINN and Emoji Sentiment Ranking

Use the Bert AI model for English, Dutch, German, French, Spanish and Italian to get more precise results (slower). Standard model is faster, works for English only, is less precise, and is based on a fixed AFINN dictionary.

Keyword Relations Analysis:

please, select the node(s) on the graph see their connections...
+   ⤓ download CSV   ?

Use this feature to compare contextual word co-occurrences for a group of selected nodes in your discourse. Expand the list by clicking the + button to see all the nodes your selected nodes are connected to. The total influence score is based on betweenness centrality measure. The higher is the number, the more important are the connections in the context of the discourse.
Top Relations / Bigrams
(both directions):

⤓ Download   ⤓ Directed Bigrams CSV   ?

The most prominent relations between the nodes that exist in this graph are shown above. We treat the graph as undirected by default. Occurrences shows the number of the times a relationship appears in a 4-gram window. Weight shows the weight of that relation.

As an option, you can also downloaded directed bigrams above, in case the direction of the relations is important (for any application other than language).

Text Statistics:
Word Count Unique Lemmas Characters Lemmas Density
Text Network Statistics:
Show Overlapping Nodes Only

⤓ Download as CSV  ⤓ Download an Excel File
Network Structure Insights
mind-viral immunity:
The higher is the network's structure diversity and the higher is the alpha in the influence propagation score, the higher is its mind-viral immunity — that is, such network will be more resilient and adaptive than a less diverse one.

In case of a discourse network, high mind-viral immunity means that the text proposes multiple points of view and propagates its influence using both highly influential concepts and smaller, secondary topics.
The higher is the diversity, the more distinct communities (topics) there are in this network, the more likely it will be pluralist.
The network structure indicates the level of its diversity. It is based on the modularity measure (>0.4 for medium, >0.65 for high modularity, measured with Louvain (Blondel et al 2008) community detection algorithm) in combination with the measure of influence distribution (the entropy of the top nodes' distribution among the top clusters), as well as the the percentage of nodes in the top community.

Influence Distribution
Topics Nodes in Top Topic Components Nodes in Top Comp
Nodes Av Degree Density Weighed Betweenness

Narrative Influence Propagation:
The chart above shows how influence propagates through the network. X-axis: lemma to lemma step (narrative chronology). Y-axis: change of influence.

The more even and rhythmical this propagation is, the stronger is the central idea or agenda (see alpha exponent below ~ 0.5 or less).

The more variability can be seen in the propagation profile, the less is the reliance on the main concepts (agenda), the stronger is the role of secondary topical clusters in the narrative.
propagation dynamics: | alpha exponent: (based on Detrended Fluctuation Analysis of influence) ?   show the chart
We plot the narrative as a time series of influence (using the words' betweenness score). We then apply detrended fluctuation analysis to identify fractality of this time series, plotting the log2 scales (x) to the log2 of accumulated fluctuations (y). If the resulting loglog relation can be approximated on a linear polyfit, there may be a power-law relation in how the influence propagates in this narrative over time (e.g. most of the time non-influential words, occasionally words with a high influence).

Using the alpha exponent of the fit (which is closely related to Hurst exponent)), we can better understand the nature of this relation: uniform (pulsating | alpha <= 0.65), variable (stationary, has long-term correlations | 0.65 < alpha <= 0.85), fractal (adaptive | 0.85 < alpha < 1.15), and complex (non-stationary | alpha >= 1.15).

For maximal diversity, adaptivity, and plurality, the narrative should be close to "fractal" (near-critical state). For fiction, essays, and some forms of poetry — "uniform". Informative texts will often have "variable + stationary" score. The "complex" state is an indicator that the text is always shifting its state.

Degree Distribution:
  calculate & show   ?
(based on kolmogorov-smirnov test) ?   switch to linear
Using this information, you can identify whether the network has scale-free / small-world (long-tail power law distribution) or random (normal, bell-shaped distribution) network properties.

This may be important for understanding the level of resilience and the dynamics of propagation in this network. E.g. scale-free networks with long degree tails are more resilient against random attacks and will propagate information across the whole structure better.
If a power-law is identified, the nodes have preferential attachment (e.g. 20% of nodes tend to get 80% of connections), and the network may be scale-free, which may indicate that it's more resilient and adaptive. Absence of power law may indicate a more equalized distribution of influence.

Kolmogorov-Smirnov test compares the distribution above to the "ideal" power-law ones (^1, ^1.5, ^2) and looks for the best fit. If the value d is below the critical value cr it is a sign that the both distributions are similar.
Please, enter a search query to visualize the difference between what people search for (related queries) and what they actually find (search results):

We will build two graphs:
1) Google search results for your query;
2) Related searches for your query (Google's SERP);
Click the Missing Content tab to see the graph that shows the difference between what people search for and what they actually find, indicating the content you could create to fulfil this gap.
Please, enter a search query to discover what else people are searching for (from Google search or AdWords suggestions):

We will build a graph of the search phrases related to your query (Google's SERP suggestions).
Find a market niche for a certain product, category, idea or service: what people are looking for but cannot yet find*

We will build two graphs:
1) the content that already exists when you make this search query (informational supply);
2) what else people are searching for when they make this query (informational demand);
You can then click the Niche tab to see the difference between the supply and the demand — what people need but do not yet find — the opportunity gap to fulfil.
Please, enter your query to visualize Google search results as a graph, so you can learn more about this topic:

   advanced settings    add data manually
Discover the main topics, recurrent themes, and missing connections in any text or an article:  
Discover the main themes, sentiment, recurrent topics, and hidden connections in open survey responses:  
Discover the main themes, sentiment, recurrent topics, and hidden connections in customer product reviews:  
Enter a search query to analyze the Twitter discourse around this topic (last 7 days):

     advanced settings    add data manually

Enter a topic or a @user to analyze its social network on Twitter:

 advanced settings    add data manually

Sign Up