Crowd Behavior Mining with Virtual Environments

Abstract

This article explores ways in which virtual environments can be used for crowdsourcing and behavior mining for filling gaps within the information space of topical research. Behavior mining in this article refers to the act of harvesting the latent or instinctive behavior of participants, usually a crowd, and injecting the population behavior into a preset context, such as within a virtual environment so that the subjective behaviors and the contexts are merged. The experimental approach combines various modalities centered upon virtual environments so as to induce presence in order to bring participants into the context. This approach is new and not well studied; however, it has real potential in research dealing with behaviors and culture in reconstructed virtual environments. Two virtual environments case studies at the 2012 and 2015 Royal Society Summer Science Exhibition are presented, which demonstrate that the unique crowdsourcing activity is able to fill gaps within the information space so that answers to research questions can be more complete. Thus, by reconstructing and replicating a lost landscape, and by injecting harvested human behavior into the context of the landscape, we may be able to gather much more information than conventional methods will allow.

Exploring Landscape Engagement through a Participatory Touch Table Approach

“…Touch tables have also been utilised within museum and gallery environments as a platform with which to conduct 'crowd behavior mining', a form of behavioural crowdsourcing whereby visitors become active participants in helping to model past human behaviours in the landscape (Ch'ng 2015;Ch'ng et al 2016). Displaying lost or ancient landscapes such Stonehenge on a touch table, and enabling participants to interact with these environments and make the types of choices and decisions that ancient peoples had to make provides valuable insights to the historical and archaeological research communities.…”

Crowd Anomaly Detection Using Motion Based Spatio-Temporal Feature Analysis

“…This work proposes a novel model for pedestrian behavior analysis. In [10] a new method explored for crowd behavior analysis by incorporating virtual environments within information space of computation. This work represents behavior mining approach for crowd behavior analysis and deals with crowd merging and splitting scenario.…”

Merging the real with the virtual: Crowd behaviour mining with virtual environments

“…The studies that are being conducted are few and far between in comparison to other areas. This paper aims to develop a recent concept in crowdsourcing work termed 'crowd behaviour mining' [2] using virtual environments, and to develop a unique concept in crowdsourcing activities that can be applied beyond the case studies presented here and to other domains that involve human behaviour as independent variables. The case studies described here use data from experiments involving separate heritage projects and conducted during two Royal Society Summer Science Exhibitions, in 2012 and 2015 respectively.…”

“…'Crowd Behaviour Mining' [2] refers to "the act of harvesting the latent behaviour or instinctive behaviour of participants, usually a crowd, and injecting the population behaviour into a pre-set context or environment within which the subjective behaviours and the context are merged." 'Crowd Behaviour Mining', referred to here as CBM is a distributed approach to solving particular problems associated with missing information in large-scale research that is impossible to reproduce within any physical environment due to the limit of time and space.…”