Social Pulse: Mapping Emotional Intensity in Partially Reopened States

By: Nicole Martin, MPH

May 15, 2020

Clarabridge Analytics
Clarabridge Engage
Contact Center

Using Clarabridge’s emotional intensity score a map was developed to understand how states feel in response to their reopening status.

Date of Data Pull: 5/13/2020 7:14 PM
Source: Twitter, API Connectors
Current Volume: 2,553,735
Date Range: May 6,2020- May 13, 2020
Tweets Related to COVID-19 & Supplemental Topics Classification Models Used: WHO Framework Model, Emotions Model, & Industry Specific Models

“Back to normal,” a phrase that elicits nervousness and excitement as society yearns to get back to work or return to small social interactions, like grabbing a cup of coffee from a favorite barista. In certain states across the U.S., partial re-opening has begun, giving us a glimpse into customer experiences and how Americans feel post-COVID19. Throughout the pandemic, individuals have discussed concern for their communities as much as the individual impact the pandemic has had on them. In this post, Clarabridge explores the emotional intensity of social media conversations in partially re-opened states.

The Findings

Clarabridge aggregates public Twitter data about COVID-19 and related topics. To understand the current pulse on consumers, an aggregated view below illustrates the emotions and the intensity of emotions expressed by consumers in week nine of the pandemic. As seen in our first analysis, “fear and confusion” and “anger and frustration” continue to remain the top emotions expressed by individuals on Twitter.

Figure 1: Emotions by Emotional Intensity (May 6 – May 13)

Figure 1: Top emotions expressed on Twitter between May 6 and May 13. Emotions are grouped in descending volume, with fear and confusion having the highest volume. “Anger and frustration” and “fear and confusion” have the highest proportion of medium or high emotional intensity.

“Fear and confusion” and “anger and frustration” continue to dominate conversations on Twitter, with individuals frustrated by protocols and nervous about “normal activities” (such as shopping). As some of the Tweet vignettes suggest, the general population remains divided on the best course of action to take, sparking emotionally intense discussions. The graph below shows the emotional intensity around the specific topics of re-opening the economy, unemployment, and protests throughout the United States.

Figure 2: Emotional Intensity by Reopening, Protests & Unemployment Topics (May 6 – May 13)

Figure 2: Emotional intensity of tweets about re-opening the economy, unemployment and protests. Individuals express high intensity with regard to the protests.

The intensity around these topics shows how different discussions spark varying levels of emotional intensity. Using Clarabridge’s structured and unstructured data analytics, we can illustrate the emotional intensity of the thirty-two states that partially reopened on a map.

Using this framework Clarabridge created a model that includes the 32 states tagged “partially re-opened” on May 13, 2020[1]. To analyze emotional intensity by state, Clarabridge mapped Twitter users who tweeted with their location setting turned on (a structured attribute) to their state. However, many public tweets do not include location data. To capture more feedback for each state, keywords and phrases queries, such as those referencing a state’s local newspaper or governor, were used to add data to each grouping. Blending structured and unstructured criteria yields a more accurate and complete picture of the emotional intensity in re-opened states. Below shows a map of the United States with partially reopened states colored by emotional intensity.

Above shows the thirty-two re-opened states and their corresponding emotional intensity based on the tweets within our sample population. States with high emotional intensity include emotionally charged tweets about protests or frustration with the decisions made by their community as seen in North Carolina. Medium intensity states see a hybrid of highly charged social discourse and low intensity tweets, mentioning both the positives and negatives of reopening. Low intensity states showcase a sense of apathy towards the pandemic, indicating an “over-it” attitude.

Using Clarabridge to organize social media commentary by state provides context for companies as they decide if/how to reopen. Social listening through structured and unstructured data provides a framework to help answer questions on the readiness of the United States to move forward. As we move forward leveraging social listening provides a tool for educated decisions in real-time (discussed throughout the series), with data-driven insight.

The anonymous artist Banksy made a new painting for an English hospital which  “appeared” last week.

What’s Next

As more states re-open, the discussions on social media can give us insight into how “back to normal” feels. Next week, I will begin to assess emotional intensity around states re-opening soon compared to states already partially open. Together, we will begin to identify how emotions about re-opening vary across states and understand the challenges individuals express.


Other Articles in This Series:

Social Pulse: Redefining a Great Experience
Published May 1, 2020

Social Pulse: Readiness to Return
Published April 24, 2020

Social Pulse: Empathy Through Action
Published April 17, 2020

Social Pulse: An Opportunity to Create Trust with Consumers
Published April 9, 2020

Social Pulse: A Craving for Understanding
Published April 2, 2020

Social Pulse: The Way We See COVID-19 Relate to CX & the Globe
Published March 26, 2020

Social Pulse: How is the World Reacting to the COVID-19 Pandemic?
Published March 20, 2020

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

Nicole Martin is currently a consultant at Clarabridge. Prior to Clarabridge, Nicole received her Master of Public Health in Epidemiology from The George Washington University. During her time at GW, Nicole wrote her graduate paper on sexuality, sexual behavior, and mental health. In addition, Nicole taught as a Graduate Assistant for the Biostatistics Department at The George Washington University. During her time at Clarabridge, Nicole has worked with healthcare accounts to enrich their analytic capabilities, created customer journey maps for property and casualty insurance companies, and continued to support innovation for clients across various industry verticals.



1.] Mervosh, S., Lee, J. C., Gamio, L., & Popovich, N. (2020, April 25). See Which States Are Reopening and Which Are Still Shut Down. The New York Times.

social pulse title image
About The Social Pulse Series

Clarabridge has embarked on an independent research project to actively analyze the “emotional pulse” of social media users worldwide during the COVID-19 pandemic. The effort’s main goal is to assess how people are feeling using Clarabridge’s Natural Language Understanding to glean insights from millions of unstructured data records. We hope to inform the public, provide insights to the scientific community and educate Clarabridge customers. The analyses in this series leverages Twitter data collected beginning March 12th using keywords such as “coronavirus,” “covid19”, and “covid-19” from Twitter. We continue to refine data collection and models as the situation evolves.

Clarabridge COVID-19 Command Center 

Questions about Coronavirus? Check out the following:
Centers for Disease Control and Prevention (CDC)
World Health Organization (WHO)
Directory of Local Health Departments