CAREER: Understanding and Addressing Geographic Inequalities in Location-Aware Technologies

Northwestern University, Evanston IL

Investigators

Abstract

This research project will explore the current limitations of location-aware technologies, seek to understand the causal dynamics at work, and propose computational and sociotechnical improvements. Local search systems, peer economy platforms, intelligent routing techniques and other geographic algorithms and systems increasingly mediate our knowledge of and interactions with the physical world. However, evidence has begun to emerge that these technologies work better in some types of areas (e.g. urban) than in others (e.g. rural). If successful, this research will lead to a wide variety of benefits for areas currently under-served by location-aware technologies, benefits ranging from algorithms that are more accurate in under-served areas to new employment opportunities that involve performing on-the-ground tasks associated with location-aware technologies. The work will also provide technology designers with new tools and techniques - such as new geographic data structures and strategies for handling geographic data sparsity - that will help them ensure that the location-aware technologies of the future are maximally effective everywhere and for everyone. This research will focus on two families of location aware-technologies: volunteered geographic information-based technologies and location-aware peer economy technologies. The projects include work that will (1) model and address coverage gaps in geographically-referenced user-generated content, (2) increase our understanding of how algorithms can unintentionally adopt biased (e.g. urban-focused) worldviews and, critically, identify ways to correct for these biases, and (3) shed light on the geographic variation of price and service quality in important peer economy technologies like ride-sharing systems and peer-to-peer borrowing and rental platforms, and develop solutions for under-served areas. This project integrates research and teaching activities, and will develop new material for an existing massive open online course, which reaches a large and diverse audience.