Use this zoom link to join

“Children’s Behavior, Morality and Meaning: Re-discovering Anthropological Fieldnotes via Natural Language Processing Techniques”

Abstract: Natural language processing (NLP) techniques have become increasingly popular in social sciences and humanities, but the core problem of meaning interpretation requires in-depth expert knowledge on the particular types of texts, the contexts regarding how the texts were produced, and the local meaning systems underlying those texts. This talk features a research model of interdisciplinary collaboration between cultural anthropology and data science, through analyzing a unique and historically significant set of anthropological fieldnotes about children’s social interactions in mid-20th century rural Taiwan. In particular, naturalistic observations of children’s cooperation and conflict in a historical context provide invaluable insights into the question of “becoming a moral person.” Combining ethnographic interpretation with NLP techniques, I compare and contrast how algorithms and human-researchers “read” children’s social interactions and pose further questions about sense-making, social cognition and knowledge production. Situated at the intersection of anthropology, history, data science, and child development research, this work has broad significance for understanding human behavior through text.

Biography: Jing Xu is an affiliate assistant professor at the University of Washington. Her research primarily focuses on moral development, education and cultural transmission in contemporary China, martial law-era Taiwan and cross-cultural comparative contexts. She adopts an interdisciplinary approach that puts anthropological and psychological theories in conversation, combines ethnography, experimental and computational methods, and draws from the broad field of Chinese studies. She is also collaborating with psychologists to study children’s belief-formation and revision in politically polarized contexts. Her current research incorporates NLP techniques and social network analysis to examine a rare archive of anthropological fieldnotes, and has received funding awards from the Chiang Ching-kuo Foundation, National Academy of Education/Spencer Foundation and the Wenner-Gren Foundation.

She holds a B.A. and M.A. from Tsinghua University, China, a Ph.D. in anthropology from Washington University in St. Louis, and received postdoctoral training in psychology at the University of Washington. She is the author of The Good Child: Moral Development in a Chinese Preschool (Stanford University Press, 2017). She has published peer-reviewed articles in journals spanning multiple disciplines such as anthropology, psychology, sociology, and area studies.

The UW Data Science Seminar is an annual lecture series at the University of Washington that hosts scholars working across applied areas of data science, such as the sciences, engineering, humanities and arts along with methodological areas in data science, such as computer science, applied math and statistics. Our presenters come from all domain fields and include occasional external speakers from regional partners, governmental agencies and industry.

The 2022-2023 seminars will be virtual, and are free and open to the public.