Suhang Wang

Social media’s explosive growth and expanding global reach have given it the power to shape not only communications but societal relationships and dynamics.

For that reason, social media has increasingly become a focal point of extensive academic studies and research.  

Suhang Wang, who recently earned his doctorate in computer science from the Ira A. Fulton Schools of Engineering, saw much to be learned from the sheer volume and wide variety of information that can be gathered from social media — and how the information can be interpreted, analyzed and applied to solve challenges in areas from business, economics and industry to government, education and health care.

In the research Wang conducted as part of his doctoral studies, he explored some of the significant benefits that a deep understanding of social media networks could make possible. He focused on the rapidly advancing fields of data mining, machine learning and social media mining.

In his dissertation, “Network Representation Learning in Social Media,” which won the 2018 Fulton Schools Dean’s Dissertation Award, Wang examined social media network representation learning.

That area of study is one aspect of broader research into what the myriad uses of information technologies and networks can reveal about communications and social interaction patterns across a wide range of human endeavors. 

One particularly significant characteristic of social media data is that it is inherently linked to an array of broader networks, Wang says.

“For example, a user can follow or be followed by another user. A user can like or comment on a post,” he says. “These social behaviors result in the formation of large-scale social networks. So, analyzing social networks can help us understand social behaviors and user preferences.”

Wang’s task has been to develop novel social network representation learning algorithms that enable more and better knowledge to be gleaned from the evolution of an array of complex, robust and fluid social media networks that have been evolving over recent years.

Many types of intricate and multifaceted networks continue to develop, especially among those defined as attributed networks, plain networks, signed networks, dynamic networks and multidimensional networks — all ways of understanding interactions among social media users.

Wang’s mission is to essentially provide learning guides for those attempting to develop more effective methods, formulas and techniques for translating the wealth of data on social media networks into informed endeavors to improve communities, countries and the world.

Wang, who is from the coastal city of Ningbo in China’s Zhejiang Province, earned his undergraduate degree in electrical and computer engineering from Shanghai Jiao Tong University, followed by a master’s degree in electrical engineering systems from the University of Michigan.

For his doctoral studies, Wang says he chose the School of Computing, Informatics, and Decision Systems Engineering in the Fulton Schools for its strong reputation in both education and research — and for the quality of its faculty, particularly Professor Huan Liu, who was his research advisor.

Collaborating with Liu and other researchers in the school was among the most valuable experiences of his career, he says.

The success of his efforts with those colleagues helped Wang obtain a position as an assistant professor with the College of Information Sciences and Technology at Penn State University.

In that role Wang says he expects to continue making research advances in data mining and machine learning for applications in mining knowledge from social media networks.

“As an educator,” he says, “I’ll cultivate the next generation of researchers and engineers” in those areas of computer science and related fields.