RWVW 2014 - The Second Workshop on Predicting Real World Behaviors From Virtual World Data

Virtual worlds refer to shared persistent massive online spaces where hundreds of thousands and even millions of people can interact with one another. Examples of such spaces include massive multiplayer online games like World of Warcraft, Eve Online etc and structured environments like SecondLife. There is a growing body of literature that focuses on the similarities and differences between how people behave in the offline world vs. how they behave in these virtual environments. Data mining has aided in discovering interesting insights with respect to how people behave in these virtual environments. Given that there is a vigorous debate at the heart of this domain with respect to the methodological limitations and the limitations of inferences across the boundaries of the real and the virtual that there is a need for a workshop that provides a common platform for discussion of challenging problems and potential solutions in this emergence field. The Workshop on Predicting Real World Behaviors from Virtual Worlds Data (VRVW) workshop will provide a critical and essential forum for integrating various research challenges in this domain and promote collaboration among researchers from academia and industry to enhance the state-of-art and help define a clear path for future research in this emerging area. This workshop is interested in research that seeks to bridge the divide between connecting online and offline behaviors. Topics of interest include prediction, mining and analysis of offline characteristics and behaviors from online data and vice versa. This workshop will facilitate collaboration among different disciplines including computer science, game studies and the social sciences.
Workshop Motivation
Computational Social Science is an emerging field which lies at the intersection of big data, behavioral data mining and traditional techniques in the social sciences. Given the nature and the range of behaviors and affordances that are observed in these environments a complex and rich sets of behaviors is observed in these environments. Previous analysis of these environments has yielded important insights not just about human behavior in the online realm but about offline behaviors as well. Thus it has been observed that similar constraints and affordances in online and offline environments lead to similar manners of behaviors. The mapping principle states that if sufficient mappings can be made between the affordances and circumstances between the offline and the online domain then it is possible to gain some valuable insights from the former to the later.
Virtual worlds data is not restricted to behavior information but is rich with explicit domain information such as types of virtual environments, characteristics of people e.g., demographics, political inclinations etc. and there are also ethical issues with respect to data collection and analysis. Previous work in this area has also shown that it is possible to build predictive models of people offline characteristics and even behaviors from their online behavioral data. Prior work has shown that it is possible to infer people's demographics, deviancy, propensity to act in certain situations etc. The challenges in this domain are unique as they aim to provide valuable information to behavioral scientists and sociologists with respect to the methodological usefulness and limits of virtual worlds.
Workshop Venue
The workshop is co-located with the IEEE SocialComputing 2014. The conference will be held in Beijing, China