Comparing Twitter and LODES Data for Detecting Commuter Mobility Patterns

Local and regional planners struggle to keep up with rapid changes in mobility patterns. This exploratory research is framed with the overarching goal of asking if and how geo-social network data (GSND), in this case, Twitter data, can be used to understand and explain commuting and non-commuting travel patterns.

The research project set out to determine whether GSND may be used to augment US Census LODES data beyond commuting trips and whether it may serve as a short-term substitute for commuting trips. It turns out that the reverse is true and the common practice of employing LODES data to extrapolate to overall traffic demand is indeed justified. This means that expensive and rarely comprehensive surveys are now only needed to capture trip purposes. Regardless of trip purpose (e.g., shopping, regular recreational activities, dropping kids at school), the LODES data is an excellent predictor of overall road segment loads.

Publications:  

• Comparing Twitter and LODES Data for Detecting Commuter Mobility Patterns (Full Report)
• Research Brief

This event will be held online via Zoom.

About the Speaker: Jochen Albrecht is a professor of computational geography at Hunter College, City University of New York. His general research centers on modeling and analysis of spatio-temporal phenomena. On the transportation side, Jochen specializes on multi-model modeling in realistic (complex) settings that allow decisionmakers to explore policy options. He is renowned for his work on standardizing geospatial workflows, which forms the basis of his third monograph in addition to his 56 peer-reviewed publications. Jochen serves on the board of directors for the Urban and Regional Information Systems Association, the GIS Certification Institute, and the California Geographic Information Association.