In today’s interconnected world, the dissemination of information through social media has been unprecedented. Not all information posted and shared is truthful or unbiased. In recent years, social media platforms have been used by malicious actors or groups to misinform and manipulate thus threatening our society at large. Social media can be easily weaponized to sow discord, thus fomenting unrest amongst audiences with the intent to create behavior change. The latest IEEE Internet Computing special issue on cyber social health highlights developments of social media analytics used to gain a better understanding of online human behavior, as research in social media analytics has seen significant development of new and advanced techniques. 

In the special issue “When the Bad is Good and the Good is Bad: Understanding Cyber Social Health Through Online Behavioral Change“, guest editor Dr. Nitin Agarwal along with co-editors Drs. Ugur KursuncuHemant Purohit, and Amit Sheth introduce a conceptual design that demonstrates modeling at cognitive, neural, and social levels for cumulative measurements in prediction, explainability, and mitigation of misinformation. 

Conceptual design that demonstrates modeling at cognitive, neural, and social levels for cumulative measurements in prediction, explainability, and mitigation of misinformation.

“In spite of significant progress in technologies to fight negative uses of social media, it has been challenging to detect, monitor, counter and overcome the malevolent behaviors and use by ill-intentioned actors,” the article stated. In the article, they describe thick data modeling and its utility to understand the content, its flow in a network, the trust and provenance factors, and the diffusion of harmful content. Several studies and examples of malicious online information campaigns are highlighted to stress the urgent need for advanced social media analysis techniques.  Of note, a bi-lateral research approach with the State of Arkansas Attorney General’s Office highlighted COVID-19 misinformation, resulting in a rich database that is live at https://cosmos.ualr.edu/covid-19 and updated constantly. Dr. Agarwal said, “the collaboration serves as a much needed model for bridging science and policy through technology to combat misinformation.”

In addition research of botnet evolution in propaganda dissemination, and disinformation campaign coordination showcase contributions of COSMOS researchers. All of which provide a cornerstone for the conceptual design annotated above. 

This special issue presents several relevant studies addressing computational techniques from natural language processing, statistics, network science, data mining, machine learning, computational linguistics, human-computer interaction, and cognitive science. Overall, misinformation is now routinely opposed or confronted due to the overall emphasis in new research being produced amongst academia, which provides the new foundation for skepticism for target audiences amongst the many platforms that exist. 

Due to the popularity of the research topic, this is a two-part special issue. The second part of the special issue is slated to appear in the March-April 2021 issue of IEEE Internet Computing magazine.