Crowdsourcing

About: Crowdsourcing is a research topic. Over the lifetime, 12889 publications have been published within this topic receiving 230638 citations.

Accurate attribute mapping from volunteered geographic information: issues of volunteer quantity and quality

Abstract: Crowdsourcing is a popular means of acquiring data, but the use of such data is limited by concerns with its quality. This is evident within cartography and geographical sciences more generally, with the quality of volunteered geographic information (VGI) recognized as a major challenge to address if the full potential of citizen sensing in mapping applications is to be realized. Here, a means to characterize the quality of volunteers, based only on the data they contribute, was used to explore issues connected with the quantity and quality of volunteers for attribute mapping. The focus was on data in the form of annotations or class labels provided by volunteers who visually interpreted an attribute, land cover, from a series of satellite sensor images. A latent class model was found to be able to provide accurate characterisations of the quality of volunteers in terms of the accuracy of their labelling, irrespective of the number of cases that they labelled. The accuracy with which a volunteer could be characterized tended to increase with the number of volunteers contributing but was typically good at all but small numbers of volunteers. Moreover, the ability to characterize volunteers in terms of the quality of their labelling could be used constructively. For example, volunteers could be ranked in terms of quality which could then be used to select a sub-set as input to a subsequent mapping task. This was particularly important as an identified subset of volunteers could undertake a task more accurately than when part of a larger group of volunteers. The results highlight that both the quantity and quality of volunteers need consideration and that the use of VGI may be enhanced through information on the quality of the volunteers derived entirely from the data provided without any additional information.

The Role of Social Networks in Emergency Management: A Research Agenda

Abstract: Lack of relevant information, particularly geospatial information, is one of the major challenges in emergency management. In the past few years, geospatial information created by volunteers and facilitated by social networks has become a promising data source in time-critical situations. This paper discusses the roles that social networks can play in the crowdsourcing of geospatial information for emergency management, data generation and dissemination through social networks, and investigates the relationships and interactions in social networks. Research issues arise in the areas of data access, data quality, information synthesis, emerging patterns of human behaviors in emergencies, analysis and visualization of nested social networks, implementation of information systems for emergency management, privacy, and equity. internationally, is more difficult to estimate. Modern technologies, especially remote sensing and GIS, have been used to monitor the situation, to locate damaged areas, and to assess severity. Yet despite this, the full potential of geospatial data generation and dissemination mediated by information technology has not been fully realized in crisis situations (NRC, 2007). Geospatial information provided by governments is inadequate in emergencies because of cost and long production cycles, while massive volumes of imagery from satellites and aircraft may be more timely but are limited to phenomena that can be seen from above. In the past few years, an alternative source of data has emerged, created by citizen journalists who collect, report, and DOI: 10.4018/jiscrm.2010100104 International Journal of Information Systems for Crisis Response and Management, 2(4), 48-58, October-December 2010 49 Copyright © 2010, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. disseminate information. Such volunteered geographic information (VGI) (Goodchild, 2007) is created by amateurs using online mapping services over the Internet, such as OpenStreetMap (OSM) or Ushahidi. VGI has been proved useful in rapidly developing emergencies such as the recent Santa Barbara fires (Goodchild & Glennon, 2010), where the need for timeliness often outweighs concerns about accuracy. During the 2010 Haitian Earthquake, a mapping community was formed immediately by people all over the world, and geospatial data about Port-au-Prince were quickly generated using OSM, and used in the rescue effort. Social networks have proven critical in such situations, because they are able to mobilize the necessary volunteers; to provide the means to share tools; and to facilitate the loose kinds of dispersed organization that are needed to make the efforts of volunteers run smoothly. In this paper we outline some of the open questions that have arisen in this context and that together might form the basis for a research agenda aimed at improving our understanding of the role social networks can play in time-critical community mapping. The paper is based on discussions that occurred in December, 2010, at a specialist meeting organized by the Center for Spatial Studies of the University of California, Santa Barbara, on the topic of Spatio-Temporal Constraints on Social Networks. At the meeting over 40 specialists from around the world discussed the state of the art in this area, the topics that needed to be researched and appropriate priorities for each topic. Although the meeting covered much broader ground, this paper focuses on the specific domain of emergency management, and summarizes the relevant discussion. Full details of the meeting, including the position papers prepared by the participants, the presentations made during the meeting, and reports of the various discussion groups, can be found at http://www.ncgia.ucsb. edu/projects/spatio-temporal/. The rest of this paper is organized as follows. The next section discusses pressing issues in the use of geospatial data and tools for emergency management. The following section then discusses the potential benefits of integrating studies on social networks into this context, followed by a series of research questions raised by this integration. The paper ends with some concluding remarks. EMERGENCY MANAGEMENT In emergencies, there is a critical time constraint on evacuating affected people, locating and delivering available resources, as well as generating relevant information and distributing it to appropriate parties in a timely manner. Relevant data are crucial to making informed decisions about where to focus attention and where to distribute limited resources; however, how to obtain reliable, accurate, and timely geospatial data is always a challenge, especially in situations where disasters develop rapidly. It is extremely difficult for government agencies to send a sufficient number of trained people to the affected area for mapping and data collection. When a disaster happens, professional emergency workers are rapidly overwhelmed and scarce emergency services may be quickly depleted. In the report to the US Congress on Hurricane Katrina, Secretary of Homeland Security Michael Chertoff emphasized “the importance of having accurate, timely and reliable information about true conditions on the ground” and pointed out that the response efforts during Katrina “were significantly hampered by a lack of information from the ground” (Chertoff, 2005). Another primary challenge in handling emergencies is information sharing and communication in order to facilitate coordination. Information needs to be appropriately shared and promptly exchanged between involved parties at the appropriate place and time. Professional emergency workers may have a special emergency management system to communicate with each other and between departments at federal, regional, and local levels. Effective communication is also vital between emergency managers and local residents for execution of evacuation plans, and between residents to help 9 more pages are available in the full version of this document, which may be purchased using the "Add to Cart" button on the publisher's webpage: www.igi-global.com/article/role-social-networks-emergency-

WearWrite: Crowd-Assisted Writing from Smartwatches

Abstract: The physical constraints of smartwatches limit the range and complexity of tasks that can be completed. Despite interface improvements on smartwatches, the promise of enabling productive work remains largely unrealized. This paper presents WearWrite, a system that enables users to write documents from their smartwatches by leveraging a crowd to help translate their ideas into text. WearWrite users dictate tasks, respond to questions, and receive notifications of major edits on their watch. Using a dynamic task queue, the crowd receives tasks issued by the watch user and generic tasks from the system. In a week-long study with seven smartwatch users supported by approximately 29 crowd workers each, we validate that it is possible to manage the crowd writing process from a watch. Watch users captured new ideas as they came to mind and managed a crowd during spare moments while going about their daily routine. WearWrite represents a new approach to getting work done from wearables using the crowd.

Improving IoT Data Quality in Mobile Crowd Sensing: A Cross Validation Approach

Abstract: Data quality, or sometimes referred to as data credibility, is a critical issue in mobile crowd sensing (MCS) and more generally Internet of Things (IoT). While candidate solutions, such as incentive mechanisms and data mining have been well explored in the literature, the power of crowds has been largely overlooked or under-exploited. In this paper, we propose a cross validation approach which seeks a validating crowd to ratify the contributing crowd in terms of the sensor data contributed by the latter, and uses the validation result to reshape data into a more credible posterior belief of the ground truth. This approach consists of a framework and a mechanism, where the framework outlines a four-step procedure and the mechanism implements it with specific technical components, including a weighted random oversampling (WRoS) technique and a privacy-aware trust-oriented probabilistic push (PATOP2) algorithm. Unlike most prior work, our proposed approach augments rather than redesigning existing MCS systems, and requires minimal effort from the crowd, making it conducive to practical adoption. We evaluate our proposed mechanism using a real-world MCS IoT dataset and demonstrate remarkable (up to 475%) improvement of data quality. In particular, it offers a unified solution to reconciling two disparate needs: reinforcing obscure (weakly recognizable) ground truths and discovering hidden (unrecognized) ground truths.

Towards Crowd-Based Requirements Engineering A Research Preview

Abstract: [Context and motivation] Stakeholders who are highly distributed form a large, heterogeneous online group, the so-called “crowd”. The rise of mobile, social and cloud apps has led to a stark increase in crowd-based settings. [Question/problem] Traditional requirements engineering (RE) techniques face scalability issues and require the co-presence of stakeholders and engineers, which cannot be realized in a crowd setting. While different approaches have recently been introduced to partially automate RE in this context, a multi-method approach to (semi-)automate all RE activities is still needed. [Principal ideas/results] We propose “Crowd-based Requirements Engineering” as an approach that integrates existing elicitation and analysis techniques and fills existing gaps by introducing new concepts. It collects feedback through direct interactions and social collaboration, and by deploying mining techniques. [Contribution] This paper describes the initial state of the art of our approach, and previews our plans for further research.