Computational Urban “Science”
Researchers have used large quantities of online data to study social dynamics in new ways. That tremendous effort resulted in the emergence of a new research area called “computational social science”. Consider the specific case of online networked individuals (e.g., users of Twitter, Instagram, Flickr). Can their social dynamics be used to build better tools for future cities? To answer that question, a few years ago, our research started to focus on understanding how people psychologically experience the city. We used computer science tools to replicate 1970s social science experiments at scale, at web scale. The result of that research has been the creation of new maps, maps where one does not only find the shortest path but also the most enjoyable path . What if we had a mapping tool that would return the most enjoyable routes based not only on aesthetics but also based on smell and sound? This talk will address that question by showing how a creative use of social media can tackle hitherto unanswered research questions (e.g., how to capture smellscapes and soundscapes of entire cities ).
Mining Open Datasets for Transparency in Taxi Transport in Metropolitan Environments
Uber has recently been introducing novel practices in urban taxi transport. Journey prices can change dynamically in almost real time and also vary geographically from one area to another in a city, a strategy known as surge pricing. In this paper, we explore the power of the new generation of open datasets
towards understanding the impact of the new disruptive technologies that emerge in the area of
public transport. With our primary goal being a more transparent economic landscape for urban commuters, we provide a direct price comparison between Uber and the Yellow Cab company in New York.
We discover that Uber, despite its lower standard pricing rates, effectively charges higher fares
on average, especially during short in length, but frequent in occurrence, taxi journeys.
Building on this insight, we develop a smartphone application that offers a personalized consultation to mobile users on which taxi provider is cheaper for their journey. By combining different types of data, Uber API, our App, Yellow Cab and Foursquare data, we show how it is possible to estimate customer
demand within an area, and by extension surge pricing, with high accuracy.
New data on urban mobility: old and new questions, new tools and pitfalls
New datasets from new sources (mobile phones, GPS, RFIDs, etc.) allow to get
access to information essential in the understanding of human mobility. This recent
availability of data which allows to answer old questions and to ask new ones
requires to develop new tools in order to extract useful information. I will illustrate these different
points with mobile phone data and I will end this presentation with a discussion on
our current quantitative understanding of human mobility in cities.
Places and Tastes: Understanding Where People are and What They Do There
Foursquare has built a large data pipeline to match geographical coordinates to specific venues and shapes. This talk will be about the evolution of this system and how we found features to give us maximum accuracy. It was also cover the reasons why the technology was developed and how it powers our products and our business. Foursquare also has a taste model which is used to understand which keywords are associated with venues, cities, and times. Tastes have given us a richer understanding of these venues and we will look at some of the fascinating data that compares tastes across venues, cities, languages, times of week, seasons.
Location-based Services in Urban Settings at Google Scale
In the age of ubiquitous mobile devices with increasing computation power and sensing capabilities, location-based apps and services are still facing many hurdles to accurately and truthfully understand where the user is. Solving this problem requires a multidimensional approach that spans the entire technological stack, from mobile sensors and hardware enhancements to large-scale data processing and machine intelligence.This talk will cover the technological challenges characterising the process of precisely locating a device, understanding the semantics associated with a location, and gaining insights about how users move around and experience the world.
Understanding and Optimizing Urban Dynamics using IoT
In this talk I will present our research activity around the use of digital traces to understand and model citizens dynamics and use of the city infrastructure.
Such models are then used to support decision making and optimization of the services that cities manage. The research is presented in the context of projects developed in different cities around the world, and with focus on transportation and tourism management.
Urban Dynamics and Computational Cartography
In this talk we pose a network perspective on urban dynamics. We revisit traditional gravity models and propose a novel adaptation of those that realise views of mobility dynamics in cities which can be tracked through modern technologies and datasets. We then shift our focus from mobility networks to another type
of network present in urban space: activity networks. Exploiting semantic information about places, we experimentally test existing metrics, but also propose new ones to tackle problems such as optimal retail store placement and foot traffic measurement on places. We close with a brief discussion on how such techniques and models could place the field of computational cartography on a new track
powering real world applications and services.
Fluid Neighborhoods: Preliminary Evidence from Foursquare Communities in Central London
We look at communities of Foursquare users in London identified according to the similarity of their check-in profiles. Of such communities we explore the spatial characteristics as represented by the density of their check-ins over a map of central London. The resulting “neighborhoods” are traced over time, through three time periods of three months of duration each. We show the basic statistical characteristics of the users' communities and their spatial neighborhoods. We also show their spatial correlation with five urban features, and a few common patterns that emerge over time. Finally, we follow visually, through a short video clip, how neighborhoods change in time against the “background” of fixed primary and secondary services (land uses) of central London. Though these are still preliminary results, we argue that they provide initial support to the idea that urban neighborhoods are “fluid” in space, and yet establish with fixed urban services positive spatial correlations, like “ripples against stones in a water flow”.
TimeGeo: modeling urban mobility without travel surveys
Individual mobility models are important in a wide range of application areas. Current mainstream urban mobility models require socio-demographic information from costly manual surveys, which are in small sample sizes and updated in low frequency. In this study, we propose a novel individual mobility modeling framework, TimeGeo, that extracts all required features from ubiquitous, passive, and sparse digital traces in the ICT era. The model is able to generate individual trajectories in high spatial-temporal resolutions, with interpretable mechanisms and parameters capturing heterogeneous individual travel choices. The modeling framework can flexibly adapt to input data with different resolutions, and be further extended for various modeling purposes.
Interdisciplinarity and funding in modern science
The project GALE has been the result of an interdisciplinary collaboration
between computer scientists, mathematicians and urban designers.
Whether scientists can benefit from restricting or broadening the scope of
their research still remains largely unexplored.
Drawing on some large data sets on scientific production during several
decades, I will focus here on individual scientists's
background interdisciplinarity and on the knowledge to which they are
exposed through their collaborators, presenting
some recent results on the advantages and disadvantages of
interdisciplinarity in modern science. I will also discuss how funding
impacts the way in which we collaborate, and the other way around.