Austin van Loon
General Information
My research centers around the understudied intersection of culture, identity, and intergroup conflict. My primary areas of interest are social psychology, the sociology of culture, and computational methods. I have substantive interests in U.S. political polarization. In my research, I make use of a broad range of tools, including: automated text analysis, machine learning, network analysis, experiments, and observational causal inference. Check out my personal website (austinvanloon.com) for more information!
During my time in graduate school, I was a member of the Computational Culture Lab, a member of the Polarization and Social Change Lab (PaSCL), and a Stanford Ric Weiland fellow. I am also an alumnus of the 2019 Princeton Summer Institute in Computational Social Science (SICSS). I have received project funding from the Russell Sage Foundation, The Defense Advanced Research Projects Agency (DARPA), the Lab for Social Research (LSR), as well as the Institute for Research in the Social Sciences (IRiSS). My work has been published in Management Science, American Behavioral Scientist, Social Science Research, The Proceedings of EMNLP, The Proceedings of ICWSM, PLOS ONE, Nature Human Behavior, and The Proceedings of the National Academy of Sciences (PNAS).
Publications and Writings
van Loon, Austin. In press. “Machine Learning and Deductive Social Science: An Introduction to Predictability Hypotheses”. The Oxford Handbook of Machine Learning and Sociology. (check out the preprint here)
Guilbeault, Doug, Austin van Loon, Katharina Lix, Amir Goldberg, and Sameer Srivastava. Forthcoming. “Exposure to the Views of Opposing Others with Latent Cognitive Differences Results in Social Influence – But Only When Those Differences Remain Obscured”. Management Science. (check out the preprint here)
Grossman, Igor, Amanda Rotella, Cendri A. Hutcherson … Austin van Loon … Tom Wilkening. 2023. “Insights into accuracy of social scientists’ forecasts of societal change”. Nature Human Behavior. (check out the paper here)
van Loon, Austin and Jeremy Freese. 2023. “Word embeddings reveal how fundamental sentiments structure natural language”. American Behavioral Scientist. (check out the paper here)
van Loon, Austin. 2022. “Three Families of Automated Text Analysis”. Social Science Research (50th anniversary special issue), 108:102798. (check out the paper here)
van Loon, Austin , Salvatore Giorgi, Robb Willer, and Johannes Eichstaedt. 2022. “Negative Associations in Word Embeddings Predict Anti-Black Bias Across Regions—but Only via Name Frequency”. Proceedings of the International AAAI Conference on Web and Social Media (ICWSM) 2022. (check out the paper here)
van Loon, Austin, Sheridan Stewart, Brandon Waldon, Shrinidhi K. Lakshmikanth, Ishan Shah, Sharath Chandra Guntuku, Garrick Sherman, James Zou, and Johannes Eichstaedt. 2020. “Explaining the ‘Trump Gap’ in Social Distancing Using COVID Discourse”. Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020. (check out the paper here)
van Loon, Austin. 2020. “Health Behavior Disparities Along Party Lines and Associative Diffusion”. ASA Culture Section Newsletter. (check it out here)
Matthew Salganik, Ian Lundberg, Alex Kindel … Austin van Loon … Sara McLanahan. 2020. “Measuring the predictability of life outcomes with a scientific mass collaboration”. Proceedings of the National Academy of Sciences, 117(15): 8398-8403. (check out the paper here)
van Loon, Austin, Jeremy Bailenson, Jamil Zaki, Joshua Bostick, and Robb Willer. 2018. “Virtual reality perspective-taking increases cognitive empathy for specific others”. PLOS ONE, 13(8):e0202442. (check out the paper here)
Guilbeault, Doug, Austin van Loon, Katharina Lix, Amir Goldberg, and Sameer Srivastava. “Cognitive Diversity Promotes Social Learning—But Only When Cognitive Differences Are Obscured”, Revise and Resubmit at Management Science. (check out the working paper here)
van Loon, Austin, Amir Goldberg, and Sameer Srivastava. “Imagined Otherness: Outgroup Dehumanization Arises from Perceived Schematic Difference”. (check out the working paper here)