Crowdsourcing

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

Managing Crowds in Innovation Challenges

Abstract: Crowdsourcing for innovation is typically conducted as an “innovation challenge” Despite the popularity of innovation challenges, there appears to be a growing consensus that innovation challenges do not succeed at generating solutions with competitive advantage potential This article presents three ways in which managers can assure that their innovation challenges are fruitful: foster different crowd roles to encourage contribution diversity; offer knowledge integration instructions and dual incentives; and offer explicit instructions for sharing different types of knowledge

Large-scale linked data integration using probabilistic reasoning and crowdsourcing

Abstract: We tackle the problems of semiautomatically matching linked data sets and of linking large collections of Web pages to linked data. Our system, ZenCrowd, (1) uses a three-stage blocking technique in order to obtain the best possible instance matches while minimizing both computational complexity and latency, and (2) identifies entities from natural language text using state-of-the-art techniques and automatically connects them to the linked open data cloud. First, we use structured inverted indices to quickly find potential candidate results from entities that have been indexed in our system. Our system then analyzes the candidate matches and refines them whenever deemed necessary using computationally more expensive queries on a graph database. Finally, we resort to human computation by dynamically generating crowdsourcing tasks in case the algorithmic components fail to come up with convincing results. We integrate all results from the inverted indices, from the graph database and from the crowd using a probabilistic framework in order to make sensible decisions about candidate matches and to identify unreliable human workers. In the following, we give an overview of the architecture of our system and describe in detail our novel three-stage blocking technique and our probabilistic decision framework. We also report on a series of experimental results on a standard data set, showing that our system can achieve a 95 % average accuracy on instance matching (as compared to the initial 88 % average accuracy of the purely automatic baseline) while drastically limiting the amount of work performed by the crowd. The experimental evaluation of our system on the entity linking task shows an average relative improvement of 14 % over our best automatic approach.

Crowd-sourced contact information and updating system using artificial intelligence

Abstract: A method and system for crowdsourcing and managing contact and profile information of a user's contacts, and exchanging business and personal contact information through a mobile device, personal computer, or a web application. The system comprises a crowdsourcing intelligence module that provides the software, analysis, and algorithms for automatically populating and updating an individual's contact information in a user's address book based on contributed information and changes made to the individual's profile by a large community of users. The module also automatically populates and updates business profile, captures business's external social and business profiles, and analyzes demographic information which can then be transmitted to users. Users may also search for job opportunities, review and purchase products and services, review the location of contacts in proximity to the user, and manage sales and account activities including lead generation, lead qualification, and better understanding their customer base.

CrowdMonitor: Mobile Crowd Sensing for Assessing Physical and Digital Activities of Citizens during Emergencies

Abstract: Emergencies such as the 2013 Central European flood or the 2013 typhoon Haiyan in Philippines have shown how citizens can organize themselves and coordinate private relief activities. These activities can be found in (physical) groups of affected people, but also within (digital) social media communities. There is an evident need, however, for a clearer picture of what exactly is going on to be available for use by the official emergency services: to enlist them, to keep them safe, to support their efforts and to avoid needless duplications or conflicts. Aligning emergency services and volunteer activities is, then, crucial. In this paper we present a mobile crowd sensing based concept, which was designed as well as implemented as the application CrowdMonitor and facilitates the detection of physical and digital activities and the assignment of specific tasks to citizens. Finally we outline the findings of its evaluation.