The Lucy Family Institute and the Navari Family Center for Digital Scholarship will be hosting Wenyi Shang for a seminar talk entitled: "Computational modeling of humanities data: cases of English literature and Chinese history".
Quantitative methods, when used on humanities materials, are often criticized as falling short in offering perspectival and interpretive nuances by its predominant focus on curating facts. But this is not necessarily the case. Digital humanists can use quantitative methods to investigate interpretive patterns instead of facts, and the only difference from established humanities methods is that it is computational models that are used to transform the materials and to obtain the patterns.
In this talk, I will demonstrate this with several of my projects. The topics of these projects range from English literature to Chinese history, but they all used computational models to deal with humanities data in order to address humanities problems. In the first project, I built classification models on 30,704 English poems to investigate the relative importance of lexical and prosodic features for the sake of disentangling “form” from other aspects of “genre.” The second project on Chinese history constructed the aristocratic social network in Eastern Jin (317–420 C.E.) China, and analyzed the network by various methods including network simulation, ERGM, community detection, and centrality measures. The results suggested a notable degree of social cohesion that united the aristocratic families as a status group during the period.
Wenyi Shang is a third-year Ph.D. candidate of the School of Information Sciences at the University of Illinois Urbana-Champaign. Working with his advisor, Professor Ted Underwood, his research focuses on digital humanities. Prior to joining the University of Illinois, he earned a bachelor’s degree in information management at Peking University, China. His current research investigates different types of humanities data, such as large-scale literary texts, historical documents, data in relational databases, and bibliographic metadata, in order to address humanities problems (mostly on history and literature). He has published in multiple digital humanities and information science journals and conferences: Digital Humanities Quarterly, Journal of Historical Network Research, Digital Humanities Conference, iConference, among others, where he adopts a variety of computational methods, including text mining, machine learning, and social network analysis.