Measuring collective attention in online content

Siqi Wu

Abstract: Siqi Wu is a postdoctoral research fellow in the Center for Social Media Responsibility at the University of Michigan (Ann Arbor). Prior to that, he was a research fellow in the Computational Media Lab at the Australian National University, where he also completed his Ph.D. (Computer Science). His research interests include computational social science, social computing, and crowd-sourcing systems. He has published papers at ICWSM, CSCW, CIKM, WWW, and WSDM. He has received one best paper honorable mention award at CSCW and one best paper finalist award at ICWSM. He was also a recipient of the Google PhD fellowship. More information about Siqi's work can be found at https://avalanchesiqi.github.io In his thesis, Siqi focused on understanding how online content captures collective human attention. He tackled a series of questions, including (a) how does Twitter API's sampling mechanism impact common measurements? (b) why do some YouTube videos keep the users staying longer? (c) how does YouTube recommender system drive user attention? (d) how do liberals and conservatives engage in cross-partisan discussions online? and (e) how does online attention transcend across platforms, across topics, and over time? Altogether, his research explores the collective consumption patterns of human attention in digital platforms. Methods, observations, and software demonstrations from his work can be used by content owners, hosting sites, and online users alike to improve video production, recommender systems, and advertising strategies.