Finger on the Pulse: Towards a Real-time City Health Monitor
Download as PPTX, PDF
3 likes1,214 views
This document discusses using social media and transportation data to monitor socioeconomic deprivation levels in cities. It presents three hypotheses: (1) deprivation is connected to "unexpected" mobility patterns, (2) higher bus versus tube use, and (3) lower social/geographic diversity. The analyses found deprivation significantly correlated with residuals from a gravity model of passenger flow, bias toward bus/car use over tubes, and lower diversity. Combining these factors explained over half the variance in a living environment deprivation measure. The document concludes timely monitoring of transportation and social media data can help allocate resources to address urban inequality.
![Talk of the City [ICWSM12]
social media
environment
sports
health Royal wedding
Spanish/Portuguese
celebrity gossips](https://image.slidesharecdn.com/pulsecscw13-130227101428-phpapp02/85/Finger-on-the-Pulse-Towards-a-Real-time-City-Health-Monitor-8-320.jpg)
Finger on the Pulse: Towards a Real-time City Health Monitor
- 1. FINGER ON THE PULSE Monitoring Health of the City Chris Smith, Daniele Quercia, Licia Capra
- 3. census deprivation + data
- 4. census deprivation + londoners on twitter
- 5. census deprivation + sentiment
- 6. predicting socioeconomic well-being with twitter r=.350 word count r=.365 MaxEnt
- 7. census deprivation + topics
- 8. Talk of the City [ICWSM12] social media environment sports health Royal wedding Spanish/Portuguese celebrity gossips
- 9. census deprivation + tube trips
- 12. Proposal
- 13. Proposal
- 14. Proposal Deprivation might be connected to: HP1: unexpected mobility HP2: use of bus (compared to tube use) HP3: low social/geographic diversity
- 15. Hypothesis 1 build a gravity model ~ flow of passengers
- 16. What is a gravity model? a b Pi Pj Tij = k g dij Pj Pi dij
- 18. Hypothesis 1 gravity works: r= .72!
- 19. Hypothesis 1 Where the model fails to fit well unexplained bit: prevailing socioeconomic factors ?
- 20. Hypothesis 1 Where the model fails to fit well unexplained bit: prevailing socioeconomic factors ? We look at (gravity)Residuals
- 21. Hypothesis 2 #tube passengers proportional to population Bus/Car bias: residual between #passengers and population
- 22. Hypothesis 3 Social/Geographic diversity: socio-economic advantage Social/Geo diversity
- 23. Hypothesis 1+2+3 Gravity Residuals *** Bus Bias ** Socio/Geo Diversity n.s.s. R^2= 9% IMD R^2= 34% Living Environment
- 24. Hypothesis 1+2+3 (top+bottom only) Gravity Residuals *** Bus Bias ** Socio/Geo Diversity n.s.s. R^2= 27% IMD R^2= 54% Living Environment
- 25. 永姻艶糸庄界岳庄稼乙
- 26. 永姻艶糸庄界岳庄稼乙
- 27. 永姻艶糸庄界岳庄稼乙
- 28. So what? Strong Passenger flowurban deprivation (timely & effective & longitudinal)
- 29. Situation (Its already 75% in the USA)
- 30. Situation By 2025 another 1.2 billion living in urban areas
- 31. Situation Cities in developing countries: 5M new inhabitants each month
- 32. Problem Inequality! Timely allocation of scarce resources
- 33. census deprivation + mental maps
- 35. draw a map
- 39. launched few months ago & > 2K players
- 40. Visibility & Social Deprivation
- 41. FINGER ON THE PULSE Monitoring Health in the City Chris Smith, Daniele Quercia, Licia Capra
Editor's Notes
- #2: explain titleshould have included a subtitle
- #13: we use the gravity model to study flows of passengers on Londons rail system.extensive network. 588 stations. click for oyster card.oyster cards record the point and time of entry and link all journeys to a user id, so we can analyse individual travel patterns.stats 1 month = 77 million journeys by 5 million users between 588 stations.
- #14: we use the gravity model to study flows of passengers on Londons rail system.extensive network. 588 stations. click for oyster card.oyster cards record the point and time of entry and link all journeys to a user id, so we can analyse individual travel patterns.stats 1 month = 77 million journeys by 5 million users between 588 stations.
- #15: we use the gravity model to study flows of passengers on Londons rail system.extensive network. 588 stations. click for oyster card.oyster cards record the point and time of entry and link all journeys to a user id, so we can analyse individual travel patterns.stats 1 month = 77 million journeys by 5 million users between 588 stations.
- #16: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #17: [describe diagram] in analogy with Newtonsclick for equation[describe equation] k, alpha, beta, gamma are normally fitted to the particular system being modeled----- Meeting Notes (13/06/2012 16:31) -----add symobols to picture
- #19: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #20: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #21: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #22: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #23: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #24: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #25: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #26: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #27: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #28: Our proposal is to use AFC data in order to build a well established form of interaction model the gravity model to describe the flow of passengers on public transport systems.introduced by Zipf in 1946 successfully used to help explain flow of humans, goods, information and disease, at inter-city level and above.
- #29: we use the gravity model to study flows of passengers on Londons rail system.extensive network. 588 stations. click for oyster card.oyster cards record the point and time of entry and link all journeys to a user id, so we can analyse individual travel patterns.stats 1 month = 77 million journeys by 5 million users between 588 stations.
- #30: the world is currently undergoing a massive influx of people into cities.which means that (next slide)
- #31: the world is currently undergoing a massive influx of people into cities.which means that (next slide)
- #32: the world is currently undergoing a massive influx of people into cities.which means that (next slide)
- #33: in particular, transport analysts and planners need to be able to understand and predict passenger flowso far there has been little work on modeling flows on public transport systems in an urban environment, or at the intra-city level.one reason for this may be lack of data, but with adoption of AFC in cities all over the world, this data is now readily available.
- #42: explain titleshould have included a subtitle