×  ⁝⁝ 
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)

Network Graph Data:

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

Visible Statements (Tagged):

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

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:


About this Context Graph:

total nodes:  extend
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.

excited about the possibilities of artificial intelligence. We aim to build the smartest possible programs that serve us. But what if this approach, actually, was the opposite of what we should aim for, instead of building the smartest AI possible. What if we aim to build a set of ai components that were the minimum of cleverness necessary for a given task and become an infrastructure component on which other AI systems would be then built. My name is David Orban, and this is the context season four episode eight

   edit   deselect   + to AI



   edit   deselect   + to AI


the, when many decades ago, the protocols for the Internet were designed the TCP IP set of standards, the architects of that design were able to realize that it would have been impossible to predict the type of applications that in the future will be built on top of those protocols using those protocols. And as a consequence, they did not try to forecast what the features would be needed, what types of applications that were emerging. A would BA.

   edit   deselect   + to AI


There's a consequence they didn't try to forecast the type of applications that would emerge, and the type of features that these applications would need, what they did instead is to agree on the minimum set of protocol components, that would be able to support the richest set of applications, whatever, creative, developers came up with in the future. And this approach has been transformative, because they assumed that the network would be done. The network wouldn't know wouldn't care, you could connect two points, you could transmit packets and whatever those two points were, whatever the content of the packets were the network, didn't care, The protocols didn't care. Now, many decades later, the internet is everywhere, and it did indeed transform the world, and lived up to. Even the wildest dreams and expectations of its architects, its developers and its users. Today, we are building a new generation of tools that take for granted. Very powerful processing power, increasingly

   edit   deselect   + to AI


available not only in data centers with dedicated specialized hardware, but in our edge devices as well. In the smartphones but also in the nodes of the Internet of Things, components that don't interact directly with humans. They have sensors, they have actuators they communicate with each other, they compute they memorize, they know more and more about the world that but the value that they provide in the network is to watch other network components, they never talk directly to humans. The amount of data that both humans are generating in this new infrastructure layer, as well as the machine components the nodes of the Internet of Things generate is enormous. And this is where the third component of this new infrastructure comes into play. algorithms that are able to recognize patterns to obtain knowledge from the raw data that encompasses the world. So we are now using all kinds of new types of terminologies, to talk about these approaches and these infrastructures, Internet of

   edit   deselect   + to AI


Things is one of them industry 4.0 digital twins, smart cities, and all of these approaches. Almost all of them suffer from almost all of these approaches suffer from the.

   edit   deselect   + to AI


Almost all of these approaches suffer from the assumption that the algorithms should be the smartest possible, rather than a,

   edit   deselect   + to AI


almost all of these approaches suffer from the assumption that the algorithms should be the smallest possible pushing their capabilities ever further. And in this way, making new implicit assumptions that go in what is called the application layer of what kind of applications should be enabled by these algorithms that run on the smart and powerful processors, using the large amount of data that we have collected and we are collecting. But these assumptions are necessarily wrong. Even if they get a few of the applications right, the probability that there will be 1000 more that are not anticipated or even worse, some essential applications that are incompatible with the capabilities of the infrastructure is almost a certainty. What we should instead aim for is analyzing and understanding what is the minimum set of smartness, what is the minimum set of ai pattern recognition that should be taken for granted, should be universally available regardless of what kind of data we are talking

   edit   deselect   + to AI


about, regardless of what kind of processor, it is running on top. The new TCP IP for artificial intelligence. And then we can be sure that eager creative and talented developers worldwide are going to be taking advantage of this new infrastructure in order to create all kinds of astounding applications for the decades to come. Do you want to live in a smart city where the definition of smart is by the architects and designers of the city from 10 years ago, rather than you having the ability of adopting whatever definition of smart is serving your interests, best in that given moment. Well, it is evident that the second approach is superior, and that it gives rise to much more adaptable, much more resilient infrastructure that welcomes a new kind of urban living, supported by the AI infrastructure that we are making available. Similarly to the smart grid. The new energy system that we are rapidly building that takes into account how solar energy, wind and batteries were together in

   edit   deselect   + to AI


order to deliver, not only a performance on par with what we used to use in our electric grid. But new possibilities as well. Again, this smart grid should not assume what are the uses what are the needs, going into the future forever, it should instead provide the minimum necessary conditions, so that those applications can be built on top with uniform assumptions that do not depend. In this case, or from the source of energy from the type of transport of the energy and so on. And I could keep going. Wherever you meet the inclusion of AI, smart, and other similar synonymous words in trying to communicate the value of some kind of technology development, you can and you should ask yourself if the designers are taking one or the other of these approaches, aiming for maximum reach covering on anticipated needs in an impossible

   edit   deselect   + to AI


quest to embrace all that is possible, or in a disciplined manner. Achieving the hard task of working out what is the minimum set of support services that the AI layer should provide uniformly to everyone. And when you do that, and you recognize that the second approach is what is being analyzed and implemented. I believe that you will see the winning team the winning approach. And, well, in a few years, or in a few decades, we will see flourishing. The new AI applications, similarly to how the Internet was able to flourish. Thanks to the same approach, starting, many decades ago. Thank you for a following this episode of the context, if you like it, you are welcome to become fan, a sponsor, a benefactor. On patreon@patreon.com, slash, David Orban,

   edit   deselect   + to AI


Show Nodes with Degree > 0:

0 0

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
Language Processing Settings:

language logic: stop words:
merged nodes: unmerge
show as nodes: double brackets: categories as mentions:
discourse structure:
×  ⁝⁝ 
×  ⁝⁝ 
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.
×  ⁝⁝ 
Main Topical Groups:

please, add your data to display the stats...
+     full stats   ?     show categories

The topics are 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   ?

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 a 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 as it allows us to better detect general patterns.

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
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.
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
Enter a search query to analyze the Twitter discourse around this topic (last 7 days):

     advanced settings    add data manually

Sign Up