Mining Behavior of Citizen Sensor Communities to Improve Cooperation with Organizational Actors

Web 2.0 (social media) provides a natural platform for dynamic emergence of citizen (as) sensor communities, where the citizens generate content for sharing information and engaging in discussions. Such a citizen sensor community (CSC) has stated or implied goals that are helpful in the work of formal organizations, such as an emergency management unit, for prioritizing their response needs. This research addresses questions related to design of a cooperative system of organizations and citizens in CSC. Prior research by social scientists in a limited offline and online environment has provided a foundation for research on cooperative behavior challenges, including ‘articulation’ and ‘awareness’, but Web 2.0 supported CSC offers new challenges as well as opportunities. A CSC presents information overload for the organizational actors, especially in finding reliable information providers (for awareness), and finding actionable information from the data generated by citizens (for articulation). Also, we note three data level challenges–ambiguity in interpreting unconstrained natural language text, sparsity of user behaviors, and diversity of user demographics. Interdisciplinary research involving social and computer sciences is essential to address these socio-technical issues. I present a novel web information-processing framework, called the Identify-MatchEngage (IME) framework. IME allows operationalizing computation in design problems of awareness and articulation of the cooperative system between citizens and organizations, by addressing data problems of group engagement modeling and intent mining. The IME framework includes: a.) Identification of cooperation-assistive intent (seeking-offering) from short, unstructured messages using a classification model with declarative, social and contrast pattern knowledge, b.) Facilitation of coordination modeling using bipartite matching of complementary intent (seeking-offering), and c.) Identification of user groups to prioritize for engagement by defining a content-driven measure of group discussion divergence. The use of prior knowledge and interplay of features of users, content, and network structures efficiently captures context for computing cooperation-assistive behavior (intent and engagement) from unstructured social data in the online socio-technical systems. Our evaluation of a use-case of the crisis response domain shows improvement in performance for both intent classification and group engagement prioritization. Real world applications of this work include use of the engagement interface tool during various recent crises including the 2014 Jammu and Kashmir floods, and intent classification as a service integrated by the crisis mapping pioneer Ushahidi’s CrisisNET project for broader impact