Anmol Madan

Time-Critical Social Mobilization

Results from a competition allow an analysis of incentives for assembling teams of unrelated people to accomplish tasks. The World Wide Web is commonly seen as a platform that can harness the collective abilities of large numbers of people to accomplish tasks with unprecedented speed, accuracy, and scale. To explore the Web’s ability for social mobilization, the Defense Advanced Research Projects Agency (DARPA) held the DARPA Network Challenge, in which competing teams were asked to locate 10 red weather balloons placed at locations around the continental United States. Using a recursive incentive mechanism that both spread information about the task and incentivized individuals to act, our team was able to find all 10 balloons in less than 9 hours, thus winning the Challenge. We analyzed the theoretical and practical properties of this mechanism and compared it with other approaches.

Social sensing for epidemiological behavior change

An important question in behavioral epidemiology and public health is to understand how individual behavior is affected by illness and stress. Although changes in individual behavior are intertwined with contagion, epidemiologists today do not have sensing or modeling tools to quantitatively measure its effects in real-world conditions. In this paper, we propose a novel application of ubiquitous computing. We use mobile phone based co-location and communication sensing to measure characteristic behavior changes in symptomatic individuals, reflected in their total communication, interactions with respect to time of day (e.g., late night, early morning), diversity and entropy of face-to-face interactions and movement. Using these extracted mobile features, it is possible to predict the health status of an individual, without having actual health measurements from the subject. Finally, we estimate the temporal information flux and implied causality between physical symptoms, behavior and mental health.

Sensing the "Health State" of a Community

Mobile phones are a pervasive platform for opportunistic sensing of behaviors and opinions. Three studies use location and communication sensors to model individual behaviors and symptoms, long-term health outcomes, and the diffusion of opinions in a community. These three analyses illustrate how mobile phones can unobtrusively monitor rich social interactions, because the underlying sensing technologies are now commonplace and readily available.

Social sensing: obesity, unhealthy eating and exercise in face-to-face networks

What is the role of face-to-face interactions in the diffusion of health-related behaviors- diet choices, exercise habits, and long-term weight changes? We use co-location and communication sensors in mass-market mobile phones to model the diffusion of health-related behaviors via face-to-face interactions amongst the residents of an undergraduate residence hall during the academic year of 2008--09. The dataset used in this analysis includes bluetooth proximity scans, 802.11 WLAN AP scans, calling and SMS networks and self-reported diet, exercise and weight-related information collected periodically over a nine month period. We find that the health behaviors of participants are correlated with the behaviors of peers that they are exposed to over long durations. Such exposure can be estimated using automatically captured social interactions between individuals. To better understand this adoption mechanism, we contrast the role of exposure to different sub-behaviors, i.e., exposure to peers that are obese, are inactive, have unhealthy dietary habits and those that display similar weight changes in the observation period. These results suggest that it is possible to design self-feedback tools and real-time interventions in the future. In stark contrast to previous work, we find that self-reported friends and social acquaintances do not show similar predictive ability for these social health behaviors.

Pervasive sensing to model political opinions in face-to-face networks

Exposure and adoption of opinions in social networks are important questions in education, business, and government. We describe a novel application of pervasive computing based on using mobile phone sensors to measure and model the face-to-face interactions and subsequent opinion changes amongst undergraduates, during the 2008 US presidential election campaign. We find that self-reported political discussants have characteristic interaction patterns and can be predicted from sensor data. Mobile features can be used to estimate unique individual exposure to different opinions, and help discover surprising patterns of dynamic homophily related to external political events, such as election debates and election day. To our knowledge, this is the first time such dynamic homophily effects have been measured. Automatically estimated exposure explains individual opinions on election day. Finally, we report statistically significant differences in the daily activities of individuals that change political opinions versus those that do not, by modeling and discovering dominant activities using topic models. We find people who decrease their interest in politics are routinely exposed (face-to-face) to friends with little or no interest in politics.

VibeFones: Socially Aware Mobile Phones

Todays mobile phones are essentially off-the-shelf, mass-market wearable computers. In this paper, we describe mobile social software that uses tone of voice, location and proximity information to create a sophisticated understanding of peoples social lives, by automatically mining their face-to-face and phone interactions. We describe several applications of our system-automatic characterization of social and workplace interactions, a courtesy reminder for phone conversations, and a personal trainer for dating encounters.

Mobile-IT Education (MIT.EDU): M-Learning Applications for Classroom Settings.

In this paper, we describe the Mobile-IT Education (MIT.EDU) system, which demonstrates the potential of using a distributed mobile device architecture for rapid prototyping of wireless mobile multi-user applications for use in classroom settings. MIT.EDU is a stable, accessible system that combines inexpensive, commodity hardware, a flexible sensor/ peripheral interconnection bus, and a powerful, light-weight distributed sensing, classification, and inter-process communications software architecture to facilitate the development of distributed real-time multi-modal and context-aware applications. We demonstrate the power and functionality of this platform by describing a number of MIT.EDU application deployments in educational settings. Initial evaluations of these experiments demonstrate the potential of using the system for real-world interactive m-learning applications.

GroupMedia: distributed multi-modal interfaces

In this paper, we describe the GroupMedia system, which uses wireless wearable computers to measure audio features, head-movement, and galvanic skin response (GSR) for dyads and groups of interacting people. These group sensor measurements are then used to build a real-time <i>group interest index</i>. The group interest index can be used to control group displays, annotate the group discussion for later retrieval, and even to modulate and guide the group discussion itself. We explore three different situations where this system has been introduced, and report experimental results.

Mobile Sensing Technologies and Computational Methods for Collective Intelligence

This book chapter is a review of mobile sensing technologies and computational methods for collective intelligence. We discuss the application of mobile sensing to understand collective mechanisms and phenomena in face-to-face networks at three different scales: organizations, communities and societies. We present an overview of the state-of-the art in individual behavior recognition from sensor data. We discuss related work on group behavior recognition such as face-to-face interaction, social signaling, conversation detection, and conversation dynamics. We also present a brief overview of pattern recognition methods in social network analysis for the automatic identification of groups and the study of social network evolution. We describe a sensor-based organizational design and engineering system for computational collective intelligence applications in organizations. We also provide two example applications of collective intelligence and modeling user behavior at the community scale. Finally, we investigate the impact that these new sensing technologies may have on the understanding of societies, and how these insights can assist in the design of smarter cities and countries.

Change in BMI Accurately Predicted by Social Exposure to Acquaintances

Research has mostly focused on obesity and not on processes of BMI change more generally, although these may be key factors that lead to obesity. Studies have suggested that obesity is affected by social ties. However these studies used survey based data collection techniques that may be biased toward select only close friends and relatives. In this study, mobile phone sensing techniques were used to routinely capture social interaction data in an undergraduate dorm. By automating the capture of social interaction data, the limitations of self-reported social exposure data are avoided. This study attempts to understand and develop a model that best describes the change in BMI using social interaction data. We evaluated a cohort of 42 college students in a co-located university dorm, automatically captured via mobile phones and survey based health-related information. We determined the most predictive variables for change in BMI using the least absolute shrinkage and selection operator (LASSO) method. The selected variables, with gender, healthy diet category, and ability to manage stress, were used to build multiple linear regression models that estimate the effect of exposure and individual factors on change in BMI. We identified the best model using Akaike Information Criterion (AIC) and R2. This study found a model that explains 68% (p<0.0001) of the variation in change in BMI. The model combined social interaction data, especially from acquaintances, and personal health-related information to explain change in BMI. This is the first study taking into account both interactions with different levels of social interaction and personal health-related information. Social interactions with acquaintances accounted for more than half the variation in change in BMI. This suggests the importance of not only individual health information but also the significance of social interactions with people we are exposed to, even people we may not consider as close friends.