Researchers Predict Face-to-Face Meetings from Cell Records

A team of academic and corporate researchers has come to the conclusion that, when given a choice, humans aren't quite ready to replace face-to-face interaction with completely virtual contact.

The scientists, who work at MIT's Senseable City Lab, IBM Research, Orange Labs, and Belgium's Université Catholique de Louvain, examined a year's worth of anonymized data from a major European cell phone operator to explore the relationship between people's calls and their physical location. The focus of the research was to examine whether telecommunications is ready to be a long-term substitute for physical travel.

Results of the research were published July 13 in the open source online journal PLoS ONE in a paper titled "Interplay between Telecommunications and Face-to-Face Interactions: A Study Using Mobile Phone Data."

One not-surprising finding: Seven out of 10 users who call each other at least once per month on average have shared the same space at the same time over the year, called "co-location" by the researchers. Nine out of 10 have shared the same cell tower area during that same period.

What's important about this, according to the scientists, is that co-location calls tend to precede face-to-face meetings.

"Their number is highly predictable based on the amount of calls between two users and the distance between their home locations," the report stated. This pattern suggests "a new way to quantify the interplay between telecommunications and face-to-face interactions."

In turn, that can have implications in the social sciences, urban planning, and transportation. The researchers calculated that they can deduce how often any pair of people will meet based on their calling patterns with an accuracy rate of 60 percent.

The data came from the billing records for a million-plus mobile phone users in Portugal gathered over a 12-month period in 2006 and 2007.

"Are telecommunications a substitute for travel? In the 1990s people thought so, fueling dreams of telecommuting activities from the peak of Mount Everest or, more prosaically, from our kitchen tables," said Carlo Ratti, director of the MIT Senseable City Lab and one of the paper's authors. "The results of our research actually show that, for the time being, human relationships do not sustain themselves in a virtual space alone, but need the support of exchanges in physical space."

About the Author

Dian Schaffhauser is a former senior contributing editor for 1105 Media's education publications THE Journal, Campus Technology and Spaces4Learning.

Featured

  • glowing AI symbol integrated into a stylized cloud icon, surrounded by interconnected digital nodes and translucent security shields, set against a gradient white-to-blue background with grid lines and abstract risk charts

    Cloud Security Alliance Report Plots Path to Trustworthy AI

    A new report from the Cloud Security Alliance highlights the need for AI audits that extend beyond regulatory compliance, and advocates for a risk-based, comprehensive methodology designed to foster trust in rapidly evolving intelligent systems.

  • Abstract geometric pattern with interconnected nodes and lines

    Microsoft 365 Copilot Gets Expanded AI Capabilities, Collaboration Tools

    Microsoft has announced the next updates to its Microsoft 365 Copilot AI assistant, including expanded AI capabilities in individual apps, the ability to create autonomous agents, and a new AI-powered collaboration workspace.

  • Abstract widescreen image with geometric shapes, flowing lines, and digital elements like graphs and data points in soft blue and white gradients.

    5 Trends to Watch in Higher Education for 2025

    In 2025, the trends shaping higher education reflect a continuous transformation of the higher education landscape to meet the changing needs of students and staff, while maintaining sustainable and cost-effective institutional practices.

  • AI-inspired background pattern with geometric shapes and fine lines in muted blue and gray on a dark background

    IBM Releases Granite 3.0 Family of Advanced AI Models

    IBM has introduced its most advanced family of AI models to date, Granite 3.0, at its annual TechXchange event. The new models were developed to provide a combination of performance, flexibility, and autonomy that outperforms or matches similarly sized models from leading providers on a range of benchmarks.