Johns Hopkins Measures Social Distancing by Twitter Use

social distancing

Researchers at Johns Hopkins University have turned to Twitter data to find out whether social distancing recommendations are having an effect in managing the COVID-19 pandemic. The upside: Since the start of social distancing on March 16, the movement of people across the United States has dropped by 49 percent. Yet the data varies widely by state, with some states reducing travel significantly more or less. In Alaska, for example, travel has dropped by 63 percent, while in Wyoming, it has dropped by just 22 percent.

Led by computer scientist Mark Dredze, the research team created a Twitter Social Mobility Index that uses geotagged data from Twitter to compare the movement of Americans from March 16-29 to their movement from Jan. 1-March 16. The preliminary analysis examined nearly 400 million tweets from 3.7 million users, who had tagged their tweets with a location or checked in at businesses, parks or other places. Travel reductions were most dramatic in states with social distancing measures in place.

Social distancing policies are only effective if people comply with them, pointed out Dredze. "Once you tell people to stay home, it doesn't mean everyone listens," he said. "It's important for us to understand on an ongoing basis if people are actually listening to these directives. But how do you know people are staying put? We're trying to find ways to do this that are efficient and timely."

One sign that people are taking social distancing seriously: The last two weeks have had the lowest Social Mobility Index (meaning the least movement of people) since tracking began, the researchers said.

The team plans to update the results over time as the study continues. "We want to continue to track this to see if people's movement will continue to drop or if people will people get fed up with staying home and start moving around again," said Dredze. "Understanding these behaviors will be important for decision-makers and public health researchers."

The full results, including a list of mobility reduction by state and downloadable data files, are available at socialmobility.covid19dataresources.org.

About the Author

Rhea Kelly is editor in chief for Campus Technology, THE Journal, and Spaces4Learning. She can be reached at [email protected].

Featured

  • AI robot with cybersecurity symbol on its chest

    Microsoft Adds New Agentic AI Tools to Security Copilot

    Microsoft has announced a major expansion of its AI-powered cybersecurity platform, introducing a suite of autonomous agents to help organizations counter rising threats and manage the growing complexity of cloud and AI security.

  • modern college building with circuit and brain motifs

    Anthropic Launches Claude for Education

    Anthropic has announced a version of its Claude AI assistant tailored for higher education institutions. Claude for Education "gives academic institutions secure, reliable AI access for their entire community," the company said, to enable colleges and universities to develop and implement AI-enabled approaches across teaching, learning, and administration.

  • central cloud platform connected to various AI icons—including a brain, robot, and network nodes

    Linux Foundation to Host Protocol for AI Agent Interoperability

    The Linux Foundation has announced it will host the Agent2Agent (A2A) protocol project, an open standard originally developed by Google to support secure communication and interoperability among AI agents.

  • open laptop in a college classroom with holographic AI icons like a brain and data charts rising from the screen

    4 Ways Universities Are Using Google AI Tools for Learning and Administration

    In a recent blog post, Google shared an array of education customer stories, showcasing ways institutions are using AI tools like Gemini and NotebookLM to transform both learning and administrative tasks.