notes on Engaging Data

The Engaging Data conference went very very well. Thanks to Caitlin and Francisca for their fantastic job! Few notes I’ve put quickly together:

Day 1

  • Peter Hirshberg gave a great keynote talk! He introduced interesting applications using real-time data: NYTE (use of phone calls from NY to cities around the world, City sense (tracking where people are right now), and City sourced (taking geocoded pictures and upload them directly to an official who can do something about it). Great quotes in his talk:
    • “with every augmentation comes amputations”. along those lines,  LBS turns us to starring at the screen instead of what’s around us.
    • ” Privacy is often eroded one convenience at a time” (by Chris Hughes of City Sourced)
  • A couple of researchers of SkyHook followed. They described how, by aggregating  data from GPS, cell phone towers, and wifi networks, they extract:
    • emergence bursts – lots of people come out at once
    • impedance clustering – accidents people want to get around
    • social affinity – large group of similar people

    Interestingly, they find spikes or dips with respect to a baseline level of actitivity (normal level of activity in a specific area)

  • Glen Urban of MIT Sloan introduced Ad Morphing. This system matches on line ads to individual cognitive style (e.g., deliberative/impulsive, analytical/holistic, verbal/visual). He concluded by introducing the recent migration of Ad Morphing on mobile phones (Concierge). The application would be to serve apps and ads that are useful on a phone’s screen.
  • Deborah Estrin of the Center for Embedded Networked Sensing introduced few projects:
  • Eric Paulos of CMU gave a beatiful talk that revolved around his research goals: improve science literacy, provide professional scientists with better data, develop new usage models for phones, enabling grass roots activism, & greater public understanding. From the same research group, Ian Li proposed powerful ways to improve self-awareness of physical activity.
  • Based on mobile phone calling data, Nathan Eagle is studying sex workers in Kenya (with Eduard Sanders), 150 undegrad smokers/recent quitters (with Yuelin Li), slums’ inhabitants (30% of people in slums carry mobile phones!) . He also touched on a spatial dynamic bayesian anomaly detection he developed with Eric Horvitz to answer questions including:
    • How do peoples’ movements and communications change when they get sick?
    • Calculate regional deviations from normal use and triangulate epicenter of disasters (e.g., tsunamis, earthquake)

    Great stuff!!!

  • Anmol Madan reported on his cool research on  how  things (e.g., political ideas, deseases) spread within face-to-face nets. He run an extensive study in one of the MIT dorms.
  • Michael Siegel of MIT Soan School mentioned that Japanese doctors created a system to capture EVERY piece of data in their hospital – every activity by every person (bar-code, RFID, EHR, test data). Check here & here.
  • Michiel Van Meeteren, Ate Poorthuis, and  Elenna Dugundji gave an engaging talk on mapping communities in large virtual social networks. They used twitter data to identify the indie mac community. They started from a central node and found the communities this node speaks to. The implications of this method are powerful – it may have jeopardize the protest during the recent Iranian elections. Very interesting work!!! Check the last abstract on this page.

Day 2

I was busy having meetings with my lab’s sponsors and followed just the panel session. Surprisinlgy, during the session, David Lazer pointed out that i’m the most central node in the twitter networks of the conference participants in  win (pic done using NodeXL) and engaging data (pic). wow!:-)

Comments are closed.