oa Building Tools For Dietary Health Monitoring: Studying Food Consumption Through Twitter

Food is an integral part of our lives, cultures, and well-being, and is of major interest to public health. According to the International Diabetes Federation, 23% of adults in Qatar had diabetes in 2013, being third most affected country in the Middle East and North Africa region. Diet, as a major cause of such diseases, is thus an important subject of study both on personal and societal levels. However, 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 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 somewhat controversial issue of the social nature of food by inducing two social networks using mentions and reciprocal following relationships. We show that users tend to mention food of similar caloric value as their social neighbors, such that an activation effect is detectable, but not necessarily in their geographic vicinity, suggesting more diverse local ties. In effect, we present a set of tools to track dietary behavior online which we will next apply to Qatar and the Gulf region.