MPI-INF Logo
Campus Event Calendar

Event Entry

What and Who

Using Twitter to study Food Consumption and Fitness Behavior

Ingmar Weber
MMCI
SWS Colloquium

At QCRI, Ingmar works on social media mining, web science and computational political science. Common to most of his research is the use of online data to understand offline behaviour.

Before joining QCRI, Ingmar was a research scientist at Yahoo! Research in Barcelona working in the area of web mining, analyzing large sets of user log data. Previously, he was a postdoc at EPFL working on sponsored search auctions, tag recommendation and other things. In the summer of 2008 he visited Microsoft Research Cambridge and, before starting his PhD, interned with companies in the area of public key cryptography and the Fraunhofer Institute for Industrial Mathematics. He did his PhD at the Max-Planck Institute for Computer Science and holds BA and MA degrees in mathematics from Cambridge University.

AG 1, AG 2, AG 3, AG 4, AG 5, SWS, RG1, MMCI  
Expert Audience
English

Date, Time and Location

Wednesday, 5 November 2014
10:30
60 Minutes
E1 5
029
Saarbrücken

Abstract

This talk presents two ongoing lines of work looking at how Twitter can be used to track societal level health issues.

You Tweet What You Eat: Studying Food Consumption Through Twitter; joint work with Yelena Mejova and Sofiane Abbar
Food is an integral part of our lives, cultures, and well-being, and is of major interest to public health. The collection of daily nutritional data involves keeping detailed diaries or periodic surveys and is limited in scope and reach. Alternatively, social media is infamous for allowing its users to update the world on the minutiae of their daily lives, including their eating habits.
In this work we examine the potential of Twitter to provide insight into US-wide dietary choices by linking the tweeted dining experiences of 210K users to their interests, demographics, and social networks. We validate our approach by relating the caloric values of the foods mentioned in the tweets to the state-wide obesity rates, achieving a Pearson
correlation of 0.77 across the 50 US states and the District of Columbia. We then build a model to predict county-wide obesity and diabetes statistics based on a combination of demographic variables and food names mentioned on Twitter. Our results show significant improvement over previous research. We further link this data to societal and
economic factors, such as education and income, illustrating that, for example, areas with higher education levels tweet about food that is significantly less caloric. Finally, we address the issue of the social nature of obesity (first raised by Christakis & Fowler) by inducing two social networks using mentions and reciprocal following relationships.

From Fitness Junkies to One-time Users: Determining Successful Adoptions of Fitness Applications on Twitter; joint work with Kunwoo Park and Meeyoung Cha
As our world becomes more digitized and interconnected, one's health status---a topic that was once thought to be private---is shared on public platforms. This trend is facilitated by scores of fitness applications that push health updates to users' social networks. This paper presents the behavioral patterns of social opt-in users of a popular fitness application, MyFitnessPal. Through data gathered from Twitter, we determine whether any features such as the profile, fitness activities, and social support can predict long-term retention and weight loss of users. We discuss implications of findings related to HCI and the design of health applications.

Contact

Brigitta Hansen
0681 93039102
--email hidden
passcode not visible
logged in users only

Carina Schmitt, 11/04/2014 12:16
Brigitta Hansen, 10/31/2014 10:28 -- Created document.