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.
Recent studies show that by combining network topology and node attributes, we can better understand community structures in complex networks. However, existing algorithms do not explore "contextually" similar node attribute values, and therefore may miss communities defined with abstract concepts. We propose a community detection and characterization algorithm that incorporates the contextual information of node attributes described by multiple domain-specific hierarchical concept graphs. The core problem is to find the context that can best summarize the nodes in communities, while also discovering communities aligned with the context summarizing communities. We formulate the two intertwined problems, optimal community-context computation, and community discovery, with a coordinate-ascent based algorithm that iteratively updates the nodes' community label assignment with a community-context and computes the best context summarizing nodes of each community. Our unique contributions include (1) a composite metric on Informativeness and Purity criteria in searching for the best context summarizing nodes of a community; (2) a node similarity measure that incorporates the context-level similarity on multiple node attributes; and (3) an integrated algorithm that drives community structure discovery by appropriately weighing edges. Experimental results on public datasets show nearly 20 percent improvement on F-measure and Jaccard for discovering underlying community structure over the current state-of-the-art of community detection methods. Community structure characterization was also accurate to find appropriate community types for four datasets. Moreover, our algorithm yields insightful community structures that explain the contextual relationships among communities, which helps us better understand two real-world applications of social networks.
Intelligent systems designed using machine learning algorithms require a large number of labeled data. Background knowledge provides complementary, real world factual information that can augment the limited labeled data to train a machine learning algorithm. The term Knowledge Graph (KG) is in vogue as for many practical applications, it is convenient and useful to organize this background knowledge in the form of a graph. Recent academic research and implemented industrial intelligent systems have shown promising performance for machine learning algorithms that combine training data with a knowledge graph. In this article, we discuss the use of relevant KGs to enhance input data for two applications that use machine learning --recommendation and community detection. The KG improves both accuracy and explainability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.