Research

Scoring Space: How home-seekers make sense of place, platforms and metrics

This study (my dissertation!) involved interviews (with 32 home-seekers, and 17 other housing experts) and online and in-person observations. I focused on two locations – Oakland, CA and Las Vegas, NV – and primarily interviewed people who had moved to one of these two cities within the past year or two. I found that home-seekers had multiple, sometimes contradictory, interpretations of the information presented on real estate platforms (including algorithmic price-estimates and scores of neighborhood qualities and amenities) and that these interpretations could support problematic (racialized) narratives about certain people or neighborhoods.

• Simple Scores are Messy Signals: How Users Interpret Scores on Real Estate Platforms. E Resor. (2024). Proceedings of the ACM on Human-Computer Interaction 8 (CSCW2), 1-25.
• [Watch this space! More articles are in the pipeline…]

Nairobi Accident Map

This project began as a collaboration between me and Ma3Route, a Kenyan transportation technology and communication platform. In 2014, the Ma3Route community was vibrant and active on social media, reporting daily road and traffic conditions in Nairobi. I suggested that we try crowdsourcing reports of road accidents to create Nairobi’s first geo-coded dataset of accident hot spots. A six-month pilot ensued, during which time I created a database of local landmarks with approximate coordinates to use for geo-coding the reports (because most Ma3Route users did not include GPS coordinates with their posts) (see Resor 2019). We ran the pilot in 2015, collecting 7,817 accident reports, that were linked to 3,941 unique accidents. The project generated positive attention from the media and local policymakers and advocates. When I left Kenya to pursue a PhD, some colleagues from the World Bank continued this work, crucially seeking to automate the process of geo-tagging and linking reports.

• Finding the local in locations: Working with GPS non-use in Nairobi. E Resor. (2019). XRDS: Crossroads, The ACM Magazine for Students 26 (2), 32-35
• Can crowdsourcing create the missing crash data? S Milusheva, R Marty, G Bedoya, E Resor, S Williams, A Legovini. (2020). Proceedings of the 3rd ACM SIGCAS Conference on Computing and Sustainable Societies
• Applying machine learning and geolocation techniques to social media data (Twitter) to develop a resource for urban planning. S Milusheva, R Marty, G Bedoya, S Williams, E Resor, A Legovini. (2021). PloS one 16 (2), e0244317

Other Projects

• Finsta: Creating” fake” spaces for authentic performance. S Dewar, S Islam, E Resor, N Salehi. (2019). Extended abstracts of the 2019 CHI conference on human factors in computing (CHI).
• The Neo‐Humanitarians: Assessing the Credibility of Organized Volunteer Crisis Mappers. E Resor. (2016). Policy & Internet 8 (1), 34-54
• Tracing a path to knowledge? Indicative user impacts of introducing a public transport map in Dhaka, Bangladesh PC Zegras, E Eros, K Butts, E Resor, S Kennedy, A Ching, M Mamun. (2015). Cambridge Journal of Regions, Economy and Society 8 (1), 113-129