Constructing a taxonomy of fine-grained human movement and activity motifs through social media

TL;DR

This paper develops a method to analyze social media data, specifically Twitter, to identify human movement patterns and activity motifs over short time scales, revealing how language and location data encode mobility behaviors.

Contribution

It introduces a novel approach to constructing a taxonomy of human movement and activity motifs using Twitter content and geolocation data, focusing on daily patterns.

Findings

Twitter data can reveal frequently visited locations and activities.

Word choice encodes spatial information.

Transition patterns form identifiable motifs.

Abstract

Profiting from the emergence of web-scale social data sets, numerous recent studies have systematically explored human mobility patterns over large populations and large time scales. Relatively little attention, however, has been paid to mobility and activity over smaller time-scales, such as a day. Here, we use Twitter to identify people's frequently visited locations along with their likely activities as a function of time of day and day of week, capitalizing on both the content and geolocation of messages. We subsequently characterize people's transition pattern motifs and demonstrate that spatial information is encoded in word choice.