Identifying Seekers and Suppliers in Social Media Communities to Support Crisis Coordination

Abstract

Effective crisis management has long relied on both the formal and informal response communities. Social media platforms such as Twitter increase the participation of the informal response community in crisis response. Yet, challenges remain in realizing the formal and informal response communities as a cooperative work system. We demonstrate a supportive technology that recognizes the existing capabilities of the informal response community to identify needs (seeker behavior) and provide resources (supplier behavior), using their own terminology. To facilitate awareness and the articulation of work in the formal response community, we present a technology that can bridge the differences in terminology and understanding of the task between the formal and informal response communities. This technology includes our previous work using domain-independent features of conversation to identify indications of coordination within the informal response community. In addition, it includes a domain-dependent analysis of message content (drawing from the ontology of the formal response community and patterns of language usage concerning the transfer of property) to annotate social media messages. The resulting repository of annotated messages is accessible through our social media analysis tool, Twitris. It allows recipients in the formal response community to sort on resource needs and availability along various dimensions including geography and time. Thus, computation indexes the original social media content and enables complex querying to identify contents, players, and locations. Evaluation of the computed annotations for seeker-supplier behavior with human judgment shows fair to moderate agreement. In addition to the potential benefits to the formal emergency response community regarding awareness of the observations and activities of the informal response community, the analysis serves as a point of reference for evaluating more computationally intensive efforts and characterizing the patterns of language behavior during a crisis.

Optimization of Orchestration of Geocrowdsourcing Activities

“…They are able to call to volunteers to geolocalize information during crisis. Other sophisticated research use information produced on social media to make sense of what is going on on a crisis area [3]. These are important steps toward a generalized approach regarding the use of crowdsourcing with a geographical context.…”

“…On our corpus (Paris) it represents respectively 50779, 12576, 3120 buckets. The number of vote k required to decide for a result (1,3,5,7,9). Again, the more vote we require, the less result we will get since more actions will be required to take a decision in each area.…”

Intent Classification of Short-Text on Social Media

“…Therefore, the nature of other kinds of complex intent (such as the broad intent class of helping) requires more thorough investigation. The closest works on crisis data analytics on Twitter has dealt with the identification of problems-aid report [3], and request-offer messages [4], [15] using only binary classifiers.…”

“…Also, this process can be complex and time consuming, given that textual data can generate a large dictionary of n-gram features. Taking a top-down approach, rule-base and pattern-aided classification have been studied for text mining problems [10], [19], [15]. We use patterns (similar to rule antecedents) as binary features to classify intent.…”

“…In another study [15], we used characteristics of communication from psycholinguistics to define a pattern set of intent expressions. We leverage these pattern sets from the prior studies in the multiclass classification context for creating binary features.…”