Welcome to the Satya Foundation

Satya means “truth” in Sanskrit and defines our purpose. The foundation is dedicated to reducing the divisions in our society by improving the quality of public discourse.

In the coming months, we will be sharing insights into the 2020 election, the world-changing events around us, and the quality of public discourse around those subjects. We use sentiment analysis technology specifically designed to deliver an accurate, unbiased, and objective view of opinions, attitudes, and emotions.

While we are a non-partisan organization, we will base our analysis on facts, and where appropriate we will voice criticism of opinions based on untruths and distortions, wherever they lie on the political spectrum.

The social media companies and other organizations that spread disinformation and pollute public discourse have vast resources. We want to help change that, but the data analysis we provide is expensive. The Satya Foundation for Improving Public Discourse is a 501(c) 3 organization. Please use the link below to help fund our work.

What Data Can You Trust?

In our post Belief or Facts, we encourage discussion based on facts. But can we trust the data that we see? Is it accurate? Is it complete? Even when there is no intent to distort or deceive, data can be misleading due to the complexities of gathering and interpreting it. Analysis by Deloitte found that more than two-thirds of survey respondents stated that the third-party data about them was only 0 to 50 percent correct. The COVID-19 pandemic has also exposed challenges collecting and analyzing data. Are increases in cases due to improved testing availability? Are deaths classified based on positive tests or symptoms? Is measuring excess deaths a better measure of the pandemic’s impact?

One of the data sources we use, sentiment analysis, is a valuable tool, but it requires a rigorous methodology to produce meaningful results:

  • Sources must be selected to ensure balanced results. Twitter generates a huge amount of data, but 80 percent of tweets come from 10 percent of users, i.e. about 2 percent of the population, potentially drowning out other opinions. To counter these effects, we curate a broad range of sources beyond the obvious Social Media to ensure that we maximize the number of individual posters sampled, and we normalize results to balance data volumes.
  • The commonly used sentiment analysis algorithms perform reasonably well at figuring out whether a piece of text is generally positive or negative. However, they fail to accurately link the sentiment expressed to a specific topic. If you have a bunch of comments that are guaranteed to be about exactly the same thing, that’s not so bad, but in the real world, people often touch on multiple topics in the same sentence. Unless sentiment analysis can assign sentiment to the correct topic, it produces a meaningless data soup. The proprietary technology we use can accurately analyze tens of thousands of inter-related topics.
  • Even if the sentiment analysis of text is accurate, the results must be interpreted with care. The Harvard Business Review found that online reviews tend to over-represent extreme views. We counter this problem by sampling widely. For example, posts on a political candidate’s Facebook page attract passionate supporters and visceral haters, but related discussion elsewhere about news items and policies can provide more nuanced views. Similarly, we don’t rely on absolute values for opinions: trends are more reliable indicators, and we further validate data by comparing with other surveys.

Data analysis in a complex world will never be perfect, and there are people deliberately trying to deceive. The more we question the data behind the facts we are fed, the closer to the truth we will get.

Beliefs or Facts?

Our sentiment analysis around COVID-19 has revealed two groups on opposite ends of the political spectrum with similar beliefs and attitudes regarding its origins, risks, and government responses to the pandemic. The first group typically falls on the progressive side of politics, while the second aligns with the Republican base, Libertarians, and alt-right. Both are characterized by some or all of the following beliefs:

  • Vaccine hesitancy or resistance.
  • Acceptance of debunked conspiracy theories such as 5G as the cause or an accelerator of COVID-19.
  • COVID-19 escaped from a Chinese lab.
  • The death rate is exaggerated.
  • Lockdowns are an unwarranted curtailment of individual freedoms.

Each group has its variations. For example, the right-leaning group, believes a Democrat conspiracy is behind the COVID-19 ‘hoax’. The progressive group is generally hostile towards Big Pharma.

What both groups have in common are beliefs that are impervious to facts, exhibiting strong confirmation bias, that is the tendency to search for, interpret, favor, and recall information that confirms or support one’s prior personal beliefs or values [1]. This bias is reinforced by social media algorithms that filter content, creating bubbles of like-minded people and ideas.

This is not a new concept. It clearly influences the political process, affecting perceptions of parties, candidates, and policies, limiting our ability to discuss the complex issues facing our society and economy. Disagreement is met with ad-hominem attacks and anger. In the case of COVID-19, these unshakable beliefs are impacting adherence to measures such as social distancing and wearing masks, and could limit the effectiveness of a vaccine if one is successfully developed. There should be open discussion about the safety of any rapidly developed vaccine, but it is likely that for many people objective facts won’t figure highly in that dialog.

As we move out of lockdowns and face a changed world, the Satya Foundation will be tracking the quality of discourse in social media, news comments, and forums, measuring the richness of discussion, empathy, and anger. Where we find openness and acceptance, we will share the enablers as widely as possible.


  1. Nickerson, Raymond S. (June 1998), “Confirmation bias: A ubiquitous phenomenon in many guises”, Review of General Psychology, 2 (2): 175–220

Our Research Methodology

The foundation is provided with sentiment analysis by our sister organization Satya Analytics. This for-profit company generates analytics and research for the travel industry, political campaigns, and other organizations. Satya Analytics uses proprietary sentiment analysis technology that delivers greater accuracy and level of detail than current techniques. They curate and sample diverse content sources to provide a range of opinions from the widest possible number of individual voices, not just common social media. Data is normalized and balanced to ensure that the few people that shout the loudest on Twitter don’t drown out the rest.

A Trump Supporter’s World is Expressed Through Negativity

Our analysis of millions of Social Media data points shows that support for Trump is more often expressed by disdain for his opponents rather than positive language towards the president. Support for his immigration policies is frequently couched in negative language aimed at immigrants, and positive statements are mainly limited to simplistic memes such as “Build the Wall”.

In contrast we find that discussion of progressive candidates is more likely to articulate support for them and their policies in positive terms.