About this Research Topic
The recent years have come with many challenges such as fast disseminating fake news and a pandemic. On the other hand, technological and infrastructure advancements have led to the availability of increasingly more data. As an example, network models for epidemics were developed well ahead of the availability of the real-world contact networks deriving from extensive contact tracing. Similarly, exceedingly more labeled data are available on information dissemination on social networks that can be leveraged to mitigate negative behavior on social media such as fake news dissemination and cyber-bullying. These have created a unique opportunity to solve the emerging problems of our times with resources in the form of connected/network data that were not available in the past. Also, novel interdisciplinary applications are being identified such as social good where Network Science and Machine Learning have not been traditionally applied. For instance, network processes and algorithms have recently been used to reduce violence among the homeless.
The goal for this Research Topic is to push the frontiers in the application of network science to problems in emerging real-world applications in epidemics, online social networks, and social good, that have been made possible only today, either due to the novelty in the application or the availability of data. Potential problems that can be addressed include understanding and containment of epidemics enabled by contact-tracing, mitigating fake news spread leveraging data from human-driven fact-checking. The topic will encourage the demonstration of novel cutting-edge research in network science, including graph learning, modeling, mining, and optimizations on real-world problems. It will also encourage strong theoretical foundations of the proposed methods to ensure that a near-optimal solution is used on a real-world problem. A key objective is to identify critical innovations that are needed to bridge the gap between the theoretical understanding of models/methods and their real-world application.
An ideal submission will be (i) based on a strong theoretical foundation, and (ii) demonstrate success on real-world data. Of particular interest would be the applications with societal impact. We welcome contributions that include, but are not limited to, the following topics:
(1) Network epidemic dynamics and containment enabled by contact tracing and spatio-temporal data
(2) Fake news detection on online social networks
(3) Peer-based interventions in real-world networks to improve people's well-being, health, and behavior
(4) Prevention of cyber abuse and harassment to promote the wellbeing of online communities
(5) Optimizing vaccine distribution
Keywords: Fake news, Social good, Urban computing, Smart connected communities, Traffic prediction, Failure detection
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.