Associate Professor Jingrui He and Arun Reddy Nelakurthi, senior engineer in machine learning research at Samsung Research America, have coauthored a new guide to user behavior modeling. Their book, Social Media Analytics for User Behavior Modeling: A Task Heterogeneity Perspective, was recently published by CRC Press.
"Recent years have seen a rapid growth in social media use, both in terms of the number of users on each platform (e.g., Twitter) and the variety of platforms being used," said He. "This book aims to analyze the rich data from social media usage, in order to address research questions of data reliability and acceptance, data heterogeneity, and model transparency and trustworthiness."
The book includes a range of models and algorithms dedicated to each of the research questions and demonstrates their successful applications across several domains, such as healthcare.
"In collaboration with Mayo Clinic Arizona, we have deployed some of our algorithms to analyze diabetes patients' online social behaviors, as well as the connections with the patients' physical markers. This book is expected to inspire future work in this exciting research area," said He.
He's research focuses on heterogeneous machine learning, rare category analysis, active learning and semi-supervised learning, with applications in social network analysis, healthcare, and manufacturing processes. Prior to joining the iSchool, He worked as a faculty member at Arizona State University and Stevens Institute of Technology and as a research staff member at IBM. Her honors include an NSF CAREER Award, IJCAI Early Career Spotlight, and two IBM faculty awards. She is the author of Analysis of Rare Categories (Springer, 2012). She earned her PhD and MS in machine learning from Carnegie Mellon University and MEng and BEng in automation from Tsinghua University.