Task assignment for social-oriented crowdsourcing
- PDF / 555,328 Bytes
- 11 Pages / 612.284 x 802.205 pts Page_size
- 78 Downloads / 171 Views
Task assignment for social-oriented crowdsourcing Gang WU
1,2
, Zhiyong CHEN1 , Jia LIU1 , Donghong HAN1, Baiyou QIAO1
1 School of Computer Science and Engineering, Northeastern University, Shenyang 110004, China 2 State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China c Higher Education Press 2020
Abstract Crowdsourcing has become an efficient measure to solve machine-hard problems by embracing group wisdom, in which tasks are disseminated and assigned to a group of workers in the way of open competition. The social relationships formed during this process may in turn contribute to the completion of future tasks. In this sense, it is necessary to take social factors into consideration in the research of crowdsourcing. However, there is little work on the interactions between social relationships and crowdsourcing currently. In this paper, we propose to study such interactions in those social-oriented crowdsourcing systems from the perspective of task assignment. A prototype system is built to help users publish, assign, accept, and accomplish location-based crowdsourcing tasks as well as promoting the development and utilization of social relationships during the crowdsourcing. Especially, in order to exploit the potential relationships between crowdsourcing workers and tasks, we propose a “worker-task” accuracy estimation algorithm based on a graph model that joints the factorized matrixes of both the user social networks and the history “worker-task” matrix. With the worker-task accuracy estimation matrix, a group of optimal worker candidates is efficiently chosen for a task, and a greedy task assignment algorithm is proposed to further the matching of worker-task pairs among multiple crowdsourcing tasks so as to maximize the overall accuracy. Compared with the similarity based task assignment algorithm, experimental results show that the average recommendation success rate increased by 3.67%; the average task completion rate increased by 6.17%; the number of new friends added per week increased from 7.4 to 10.5; and the average task acceptance time decreased by 8.5 seconds. Keywords crowdsourcing, social networks, task assignment
1
Introduction
Crowdsourcing, first proposed by Jeff Howe, the reporter of Wired magazine in June 2006 [1], is a mechanism that allows people to accomplish one task together and achieve a consistent goal [2]. As a problem-solving and production model [3], crowdsourcing has succeeded in some machine-hard problems, e.g., old books digitalization through reCAPTCHA. Nowadays, the Internet plays an important role in online crowdsourcing platform, like Amazon Mechanical Turk (AMT), where people Received April 4, 2019; accepted October 8, 2019 E-mail: [email protected]
can easily participate in specific tasks, recruit workers, monitor the task flow, and get execution results. Another example is Wikipedia which is reported to be “the best-known example of crowdsourcing . . . that far exceeds traditionally-compiled information sources, such as en
Data Loading...
