RII track-1: harnessing the data revolution for vermont: the science of online corpora, knowledge, and stories (socks) -?distant reading? Involves the use of computational methods to analyze…

RII track-1: harnessing the data revolution for vermont: the science of online corpora, knowledge, and stories (socks) -?distant reading? Involves the use of computational methods to analyze literary texts. IT is a concept with enormous unrealized potential. For example, no individual can read 100 million tweets or a century?s worth of literature or all the new york times articles ever written. However, by scaling up and harnessing data, a distant reading system can be created that does. The science of online corpora, knowledge, and stories (socks) project will undertake a grand challenge. The challenge will entail the construction and broad application of distant reading to advance the computational social sciences and digital humanities in the age of massive text-as-data online, in the same way that telescopes and microscopes have done for the physical and life sciences. This research capacity will assist in answering some enduring questions. How do ecologies of stories evolve? What insights can be derived from providing social scientists and humanities scholars with new computational instruments reflecting language use in their domain? To answer these questions and enable new programs of computationally aided research, socks will advance a data-driven, computational, ?science of stories.? Socks tools will harness the data revolution by supporting transdisciplinary research in data science, computational social science, digital humanities, and complex systems. Socks will be administered by the university of vermont & state agricultural college in collaboration with five predominantly undergraduate universities: champlain college, middlebury college, norwich university, saint michael?s college, and vermont technical college. Socks will advance initiatives grounded in principled theory and methods through the quantitative measurement of sentiment and stories across a diverse portfolio of corpora. New insights into the power and use of stories and narratives will be provided across a broad array of social, economic, and health domains through integrated data and teams. Stories are fundamental to how people comprehend, explain, and potentially shape their lives, the lives of others, and the world around them. Yet despite the power of stories, academic interest across many disciplines, and abundant online text-based corpora, a commensurate and accessible scientific platform for the measurement of stories that can support economies and communities, shape regional business strategy, and inform public policy is lacking. Building on the existing research infrastructure designed to measure and describe the shapes of stories within specific domains through meaning, characters, events, and narratives, new tools will extend n-gram analysis to the study of story-arcs and plots, and to apply theory-driven analysis to the study of stories and characters. Impacts from these data instruments will describe stories in an array of spaces including literature, mental health, public health, climate change, local and regional news media, immigration, and social media to discover plot lines, sentiment, new angles for digital marketing, and conspiratorial or MIS-information campaigns. The platform will function in near real-time for social media and news; retrospectively for digitized literature, archival documents, and other recorded texts; and will extend to any evolving complex system comprising distinct narrative components. Socks will train the next generation of students in vermont in complex systems and data science, computational social science, and provide teacher training for computer and data science to secure the long-term future of vermont?s technology industry and its associated economy. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.