InfraNodus -

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.
Example:
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.

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)

Text Mining Analytics:

Summary of insights from the analytics panel. For specific in-depth exports, see the download button in the Analytics panel.

TXT Analytics Report CSV Report N-Grams CSV

Network Graph Data:

The raw data with all the statistics for further analysis in another software.

JSON CSV Gexf (Gephi)

All the Text (for backup and duplicating):

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:

Your Project Notes

Interpret graph data, save ideas, AI content, and analytics reports.

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 am recording this episode of the context that the day that Russia invaded Ukraine and you will be watching it approximately a week later the earliest and then months or years later if you will be interested still. I don't know what will happen over the course of the next few days. But What is guaranteed is that there will be a lot of confusion and our ability to make sense of the world will also depend on the kind of tools and filters that we use in order to interpret the internet information that we receive. My name is David Orban and this is the context we have the ability to receive and absorb interpret information from a wide variety of sources to it agree that probably hasn't happened before it we have very many television channels, YouTube channels and other video content online. We have of course, journalistic sources, but we also have crowd sourced intelligence information that is coming from people on the ground or who are analyzing electronic sources of information,

16461473300000000

satellite images, even in order to aggregate and give a picture of what is happening especially in two motors tragic times, like what we are witnessing these days, the invasion of Ukraine by Russia. However, most of us are not equipped with the tools that enable the correct aggregation and synthesis of that information. In the past, we would rely on professional journalists to definitively complete this kind of important and valuable task However, over the course of the past 10 years or so, many people have started to look at the work of journalists as not only chronicling what is happening in an objective manner, but interpreting in giving a slant to that chronicle expressing their own point of view or the point of view of their editorial board. Sometimes it's self driven by a political aim. That is, at least in part, the source of a degree of mistrust that an increasing number of people have towards official sanctioned or even previously prestigous authoritative sources of

16461473300000000

information. However, this is definitely a paradox, drinking from the firehose of information is beyond our human individual capacity. And we don't trust the interpretation and aggregation of the news by the professionals. What is the solution that Max Tegmark at the Massachusetts Institute of Technology The MIT is actually conducting a research program in search of a solution and his group put together an application that you can also start using it is called improve the news and you can find it on improve the newer news dot orgy on improve the news, you have sliders available that you can actively engage with in order to get exposed to news sources that are

16461473300000000

not only a corresponding to your points of view, but also the points of view off people who you disagree with. And you can do it progressively under your own control. And there is research demonstrating that this is actually desirable, that rather than giving us refuge, further retreating in our echo chamber away from different points of view, this kind of environment where you are in charge allows people to explore an experiment more and the effect of being exposed to these alternative points of view is that of becoming less polarized, of being able to understand better in a broader context. What is going on as of today, of course, the homepage of improve the news.org is dominated by information about Ukraine, and you can read summaries of articles and what is going on in the facts. Together with pro rise, Russian and anti Russian descriptions, as well as a nerdy Addendum which links you to another very, very interesting website called Metropolis that is able to provide you with

16461473300000000

another kind of interactivity where you can actually express your view of the probability of certain outcomes of future events. Just a couple of days ago, for example, the question was, will Russia invade Ukraine? And I voted yes with a probability of 60%. And as of today, that question has resolved positively Russia indeed invaded, you can go to meticulous to check what are the open questions how the dynamically adjusting outcome in this prediction market is evolving around various open questions still, both about the Ukrainian conflict as well as other interesting things. So, understanding that we are individually biased and that our various sources are also unavoidably bias should not reduce us to paralyze the position of skepticism. And instead, it can be substituted by a more proactive stance with the help of innovative tools, like improve the news I invite you to experiment with these tools to use them to see what are the different points of view that you can explore why you

16461473300000000

disagree with them, if they represent any glimpse of information that you can actually incorporate in your worldview and leverage for future decisions. This is an important process revising your assumptions based on new information in order to update your predictions around what is going to happen. It is the so called Bayesian process of updating your priors and there are mathematical foundations to the process that research projects are leveraging. We often complain about how social media algorithms

16461473300000000

in general technology platforms manipulate us. Well, we can take things in our own hands. Every time you hide a post or you dislike a YouTube video. You are taking things in your own hands because you are telling the algorithm your own preferences. But with platforms like improved news.org You are taking a step further. You are actively shaping the kind of information that you will receive and exploring the boundaries of your own adaptability as you are exposed to different points of view. We will see what will happen over the course of the next few days and weeks. I hope that the rule of law will be really established that the Russian troops will treat and respect Ukraine's sovereignty. I hope that there will be as few casualties as possible. And we will see but in the meantime, we have to be alert and we have to be informed in these coming days. Of certainly many many reasons and sources of confusion. Thank you

16461473300000000

Show Nodes with Degree > 0:

0 0

Total Nodes Shown:
extend

Filter Graphs:

Filter Time Range

from: 0
to: 0

update metrics live

Recalculate Metrics Reset Filters

Show Labels for Nodes > 0 size:

0 0

Default Label Size: 0

0 20

labels size = nodes size
labels color = nodes color

Edges Type:

Layout Type:

Reset to Default

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:

N/A

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.

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:

Main Topical Clusters & High-Level Ideas

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.

please, add your data to display the stats...

Most Influential Keywords & Concepts

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.

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

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

please, add your data to display the stats...

Network Structure:

N/A

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.

Download: TXT Report CSV Report More Options

Structural Gap Insight

(topics to connect)

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.

N/A

Discourse Entrance Points

(concepts with the highest influence / frequency ratio)

These nodes have unusually high rate of influence (betweenness centrality) to their frequency — meaning they may appear not as often as the most influential nodes but they are important narrative shifting points.

These are usually effective entrance points into the discourse, as they link different topics together and have high inlfuence, but not too many connections, which makes them more accessible.

N/A

Emerging Keywords

N/A

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):

loading...

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):

loading...

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.

Concept Relation Analysis:

please, select the node(s) on the graph or in the table below to see their connections...

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 in 4-grams

(bidirectional, for directional bigrams see the CSV table below):

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
0	0	0	0

Text Network Statistics:

Discourse Network Structure Insights

mind-viral immunity:

N/A

stucture:

N/A

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.

We recommend to try to increase mind-viral immunity for texts that have a low score and to decrease it for texts that have a high score. This ensures that your discourse will be open, but not dispersed.

The higher is the diversity, the more distinct communities (topics) there are in this network, the more likely it will be pluralist.

Modularity	0	Influence Distribution	0 %

Topics	Nodes in Top Topic	Components	Nodes in Top Comp
0	0 %	0	0 %
Nodes	Av Degree	Density	Weighed Betweenness
0	0	0	0

Discourse Advice:

N/A

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)

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:

(based on kolmogorov-smirnov test)

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.