Enter a word to explore its sentiment and role in media narratives.


Free tools to detect AI-generated content, extract and visualize keywords from news and your texts.
Biden, Israel, Gaza, COVID, Russia, Ukraine, Trump, Putin, track mass media sentiment on any topic.

New Free ChatGPT Detector | View Topic Keywords from Media | Paste to Extract Keywords Online

Media Keywords Tag Cloud

News and mainstream media tag cloud of the hour, generated with our AI and updated in real time.

Click below to view tag cloud from media and news You can view main topics and media keywords to discover hidden patterns and systemically repeating content behind numerous news publications. Updated: Oct 15 22:05 UTC Try....

Who's dominating media and news landscape right now?

Updated: Oct 15 22:05 UTC :>

View trends of leading news topics. Our text-mining analysis is drawn from a comprehensive array of global English-language news sources and powered by AI for enhanced understanding of where the world is headed, in real time. Access data.

Trampometer

Trump (299.00) shows 121.48% higher Frequency of mentions than Biden (135.00).

Historically, Trump (mean: 276.80) tends to have 30.94% more Frequency of mentions than Biden (mean: 211.40).

Narrative centrality

Trump (5.78) shows 69.87% higher Narrative centrality than Biden (3.40).

Historically, Trump (mean: 4.88) tends to have 28.34% more Narrative centrality than Biden (mean: 3.80).

Trump (5.78) gains narrative centrality.

Backgroundness

Biden (0.26) shows 366.54% higher Backgroundness than Trump (0.06).

Historically, Biden (mean: 0.22) tends to have 83.20% more Backgroundness than Trump (mean: 0.12).

Russia and Ukraine

Ukraine (143.00) shows 50.53% higher Frequency of mentions than Russia (95.00).

Historically, Ukraine (mean: 142.76) tends to have 9.16% more Frequency of mentions than Russia (mean: 130.78).

Narrative centrality

Ukraine (4.05) shows 45.04% higher Narrative centrality than Russia (2.79).

Historically, Ukraine (mean: 3.48) tends to have 18.53% more Narrative centrality than Russia (mean: 2.94).

Ukraine (4.05) gains narrative centrality.

Backgroundness

Russia (0.44) shows 107.70% higher Backgroundness than Ukraine (0.21).

Historically, Russia (mean: 0.50) tends to have 37.96% more Backgroundness than Ukraine (mean: 0.36).

Gaza and Israel

Israel (241.00) shows 156.38% higher Frequency of mentions than Gaza (94.00).

Historically, Israel (mean: 162.34) tends to have 17.38% more Frequency of mentions than Gaza (mean: 138.30).

Narrative centrality

Gaza (2.20) shows 2.18% higher Narrative centrality than Israel (2.16).

Historically, Israel (mean: 3.70) tends to have 9.48% more Narrative centrality than Gaza (mean: 3.38).

Israel (2.16) gains narrative centrality.

Backgroundness

Gaza (0.50) shows 219.88% higher Backgroundness than Israel (0.15).

Historically, Gaza (mean: 0.33) tends to have 9.01% more Backgroundness than Israel (mean: 0.30).

Tracking BIGCRUT: Biden, Israel, Gaza, COVID, Russia, Ukraine, Trump, Putin

Updated: Oct 15 22:05 UTC

We've selected keywords: Biden, Israel, Gaza, COVID, Russia, Ukraine, Trump, Putin (we call them BIGCRUT words) to observe how mainstream media (MSM) discusses these topics. We monitor these and many other keywords, and apply AI to mine textual data into the media's handling of significant global issues and political figures. We do it in order to explore future perspectives, narratives, and agendas shaping public discourse. For each keyword we automatically measure Frequency of mentions, Narrative centrality, Backgroundness, Polarity sentiment, Sentiment inconsistency, and Subjectivity sentiment. All plots are interactive (clickable).

85%

Frequency of mentions

Term frequency measures how often BIGCRUT keywords appear in press. Simple and evident, this basic metric helps to understand the importance of keyword in media. A higher frequency suggesting potential significance or relevance across mainstream media (MSM) content.


Updated: Oct 15 22:05 UTC | Method: TF

Narrative centrality

Narrative centrality, derived from estimations of term frequency distribution parameters, measures the degree to which keyword is articulated and nuanced within news discourse. It assesses if there is coherence and focus in discussions on the topic. Is it Trump or Biden in the focus of media discussion at the moment? The higher the line, the more likely the word is in the spotlight of mainstream media attention, not simply mentioned.


Updated: Oct 15 22:05 UTC | Method: 1/sqrt_kp

Backgroundness

Backgroundness, derived from Fisher information, highlights keywords that are indispensable, commonly referred to as "amen" words, and topics heavily fixated upon by the media. Uncovers how much the topic or keyword gets into the backdrop of discussions as the time goes on. The higher the line, the more the word is part of background story, and not in the spotlight.


Updated: Oct 15 22:05 UTC | Method: 1/fisher

Sentiment analysis of news

Sentiment analysis automatically extracts emotions from mainstream media news texts. Presented here are average scores that summarize sentiment for each BIGCRUT keyword (Biden, Israel, Gaza, COVID, Russia, Ukraine, Trump, Putin) across hundreds of media contexts in a given moment. On the plots you can see how measurements change in time. These time series plots are interactive and clickable.

Polarity sentiment

Polarity sentiment score shows overall emotional tone within a time frame, associated with keywords that we track. A higher score indicates a generally optimistic or favorable context, while a negative polarity suggests a pessimistic or unfavorable sentiment. So the higher the polarity sentiment score, the more positive is the sentiment expressed in the context around the word. The lower the line on graph, the more negative is the context of the mainstream talk. Is it Trump or Biden mentioned in a positive contex by MSM? Sentiment averages that fall below zero represent doom or public outcry.


Updated: Oct 15 22:05 UTC | Method: sentiment

Sentiment inconsistency or heterogeneity

When the curve on the plot is higher, it shows more disagreement among media sources when discussing the topic. Conversely, lower values of this score suggest a more unified opinion (i.e. media consensus). This analysis measures variance values with polarity sentiment scores. It quantifies how sentiments vary across different instances of a keyword in analyzed news texts. It allows to make conclusion about the spread of sentiment. For instance, within the same hour across various media outlets, sentiments towards an individual can vary significantly. Such is an example of sentiment inconsistency. The measure is similar to opinion spread, sentiment volatility, opinion variance, divergent sentiment, attitudinal diversity, or opinion heterogeneity. It captures sentiment variability across different contexts and media outlets, reflecting the statistical concept of variance in sentiment analysis.


Updated: Oct 15 22:05 UTC | Method: sentiment

Subjectivity sentiment

Subjectivity measures the degree of personal opinion or bias in the text. A higher subjectivity score suggests a more opinionated or biased viewpoint, while a lower score indicates a more objective or factual presentation. The higher the line on the plot, the more opinionated is media discussion of the topic. Each data point represents the mean sentiment score for a given timestamp and keyword, calculated from hundreds of media contexts that are being analyzed by AI.


Updated: Oct 15 22:05 UTC | Method: sentiment

Tutorials and tools



Text mining and exegesis


Text mining is a computational technique to analyze and extract not so evident information from large bodies of text. By applying advanced algorithms and statistical models, text mining can help uncover hidden knowledge: patterns, relationships, and insights not apparent to the human reader. Read how to mine religious and literary texts.