Peter Sheridan Dodds
Director, Vermont Complex Systems Center and Professor, Department of Computer Science
Peter's research focuses on system-level, big data problems in many areas including language and stories, sociotechnical systems, Earth sciences, biology, and ecology. Peter has created (and constantly evolves) a series of complex systems courses starting with Principles of Complex Systems. He co-runs the Computational Story Lab and the MassMutual Center of Excellence in Complex Systems and Data Science with Chris Danforth.
Selected Publications
The two fundamental shapes of sleep heart rate dynamics and their connection to mental health in college students
Digital Biomarkers, July 1, 2024
Events and behaviors associated with symptoms of generalized anxiety disorder in first-year college students
PsyArXiv Preprint, June 20, 2024
Predicting stress in first-year college students using sleep data from wearable devices
PLOS Digital Health, April 11, 2024
A large clinical trial to improve well-being during the transition to college using wearables: The lived experiences measured using rings study
Contemporary Clinical Trials, Sept. 21, 2023
A blind spot for large language models: Supradiegetic linguistic information
Preprint, June 11, 2023
Park visitation and walkshed demographics in the United States
Preprint, May 20, 2023
An assessment of measuring local levels of homelessness through proxy social media signals
Preprint, May 15, 2023
Curating corpora with classifiers: A case study of clean energy sentiment online Preprint
Preprint, May 4, 2023
A decomposition of book structure through ousiometric fluctuations in cumulative word-time
Nature Humanities and Social Sciences Communications, April 29, 2023
Sentiment analysis of medical record notes for lung cancer patients at the Department of Veterans Affairs
PLOS ONE, Jan. 25, 2023
Gauging the happiness benefit of US urban parks through Twitter
PLOS ONE, March 30, 2022
Quantifying changes in the language used around mental health on Twitter over 10 years: Observational study
Journal of Medical Internet Research: Mental Health, March 30, 2022
Storywrangler: A massive exploratorium for sociolinguistic, cultural, socioeconomic, and political timelines using Twitter
Science Advances, July 16, 2021
How the world’s collective attention is being paid to a pandemic: COVID-19 related n-gram time series for 24 languages on Twitter
PLOS ONE, Jan. 6, 2021
Visitors to urban greenspace have higher sentiment and lower negativity on Twitter
People and Nature, Aug. 19, 2019
The emotional arcs of stories are dominated by six basic shapes
EPJ Data Science, Nov. 4, 2016
Human language reveals a universal positivity bias
Proceedings of the National Academy of Sciences, Feb. 9, 2015
Selected Press
UVM, MassMutual renew partnership to help people live healthier, more enjoyable lives
UVM Today, Nov. 14, 2023
Finding signals in the noise: Using data to develop personalized recipes for health
UVM Today, Oct. 10, 2023
Panic attack triggers could be predicted by tracking mood and monitoring Twitter
IFL Science, Feb. 7, 2023
The war in Ukraine has made Russian social-media users glum
The Economist, March 12, 2022
Happiness calculator vs. Alex Goldman
Reply All, Oct. 29, 2020
Is everybody doing … OK? Let’s ask social media
New York Times, Oct. 12, 2020
Has Twitter just had its saddest fortnight ever?
Nature, June 15, 2020
Inside the lab that’s quantifying happiness
Outside, Aug. 11, 2017
Your Instagram posts may hold clues to your mental health
New York Times, Aug. 10, 2017