Course Description:The popularity of wearable and mobile devices, sensors, and online social networks has generated an explosion of detailed behavioral data. These massive digital traces provide us with an unparalleled opportunity to realize new types of scientific approaches that enable novel insights about our lives, health, and happiness. However, gaining actionable insights from these data requires new computational approaches that turn observational, scientifically “weak” data into strong scientific results and can computationally test domain theories at scale.
Key challenges include appropriate data collection and preparation, computational modeling of constructs in health and social sciences to model domain knowledge and questions, appropriate design of computational experiments and observational studies, and how to infer well-being from noisy raw data, or multimodal data sources. This seminar will review progress and discuss current frontiers in each of these challenges.
We will discuss a variety of data sources (e.g., social networks, social interactions, phone data, conversation transcripts) and how to leverage these to improve human well-being (e.g., clinical use, public health, monitoring vs interventions, mental health, global health, design of online communities).
Each week will consistent of paper reading, presentation, and discussion. In contrast to the highly-curated presentation of content in a more introductory course, students will be expected to contribute to all aspects of the definition and content of this course. This will include identifying relevant content and contributing to discussion of that content.
Over the quarter, students will develop an group research project in the area of data science for human well-being.