Abstract
Plenty of previous researches focus on crowdsourcing task recommendation to protect data quality and raise task execution efficiency. However, in real life, most crowdsourcing platforms do not allow duplicate task executions due to the budget constraints, and the recommendations are usually made towards new tasks without prior knowledge due to short task lifespan. Therefore, most previous works are noy applicable due to improper assumptions. In this paper, we propose Pioneer-Assisted Task RecommendatiON (PATRON) framework to generate accurate recommendations without analyzing the tasks’ contents. We select a set of pioneer workers to collect initial knowledge of the new tasks, and adopt the k-medoids clustering algorithm to split the workers into subsets based on the worker similarity. Cluster selection and worker pruning provides accurate and efficient recommendations that satisfies the valid recommendation requirements from requesters. Evaluations conducted based on real datasets collected from Tencent SOHO show the efficiency of our proposed framework on recommendation acceptance rate and recommended worker quality.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tencent SOHO. https://soho.qq.com/tasks
Aggarwal, C.C.: Recommender Systems: The Textbook. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-29659-3
Chen, X., Deng, B.: Task allocation schemes for crowdsourcing in opportunistic mobile social networks. In: International Conference on Computing, Networking and Communications (ICNC), pp. 615–619 (2018)
Dittus, M., Quattrone, G., Capra, L.: Mass participation during emergency response: event-centric crowdsourcing in humanitarian mapping. In: Conference on Computer Supported Cooperative Work (CSCW), pp. 1290–1303 (2017)
Fan, J., Zhou, X., Gao, X., Chen, G.: Crowdsourcing task scheduling in mobile social networks. In: Pahl, C., Vukovic, M., Yin, J., Yu, Q. (eds.) ICSOC 2018. LNCS, vol. 11236, pp. 317–331. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-03596-9_22
Feldman, M., Bernstein, A.: Cognition-based task routing: towards highly-effective task-assignments in crowdsourcing settings. In: International Conference on Information Systems (ICIS) (2014)
Hu, H., Li, G., Bao, Z., Cui, Y., Feng, J.: Crowdsourcing-based real-time urban traffic speed estimation: from trends to speeds. In: IEEE International Conference on Data Engineering (ICDE), pp. 883–894 (2016)
Kumai, K., et al.: Skill-and-stress-aware assignment of crowd-worker groups to task streams. In: AAAI Conference on Human Computation and Crowdsourcing (HCOMP), pp. 88–97 (2018)
Liu, C., Gao, X., Wu, F., Chen, G.: QITA: quality inference based task assignment in mobile crowdsensing. In: Pahl, C., Vukovic, M., Yin, J., Yu, Q. (eds.) ICSOC 2018. LNCS, vol. 11236, pp. 363–370. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-03596-9_26
Ng, R.T., Han, J.: CLARANS: a method for clustering objects for spatial data mining. IEEE Trans. Knowl. Data Min. (TKDE) 14(5), 1003–1016 (2002)
Pilourdault, J., Amer-Yahia, S., Lee, D., Roy, S.B.: Motivation-aware task assignment in crowdsourcing. In: International Conference on Extending Database Technology (EDBT), pp. 246–257 (2017)
Qiao, L., Tang, F., Liu, J.: Feedback based high-quality task assignment in collaborative crowdsourcing. In: IEEE International Conference on Advanced Information Networking and Applications (AINA), pp. 1139–1146 (2018)
Safran, M.S., Che, D.: Efficient learning-based recommendation algorithms for top-N tasks and top-N workers in large-scale crowdsourcing systems. ACM Trans. Inf. Syst. (TOIS) 37(1), 2:1–2:46 (2019)
Sarma, A.D., Parameswaran, A.G., Widom, J.: Towards globally optimal crowdsourcing quality management: the uniform worker setting. In: International Conference on Management of Data (SIGMOD), pp. 47–62 (2016)
Singh, V.K., Mukhopadhyay, S., Xhafa, F.: A budget feasible peer graded mechanism for IoT-based crowdsourcing. CoRR abs/1809.09315 (2018)
Zhang, C., et al.: PMViewer: a crowdsourcing approach to fine-grained urban PM2.5 monitoring in China. In: IEEE International Conference on Mobile Ad Hoc and Sensor Systems (MASS), pp. 323–327 (2017)
Acknowledgment
This work was supported by the National Key R&D Program of China [2018YFB1004703]; the National Natural Science Foundation of China [61872238, 61672353]; the Shanghai Science and Technology Fund [17510740200]; the CCF-Huawei Database System Innovation Research Plan [CCF-Huawei DBIR2019002A]; the Huawei Innovation Research Program [HO 2018085286]; the State Key Laboratory of Air Traffic Management System and Technology [SKLATM20180X], and the Tencent Social Ads Rhino-Bird Focused Research Program. Xiaofeng Gao is the corresponding author.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Xia, Y., Xu, Z., Gao, X., Chi, M., Chen, G. (2019). PATRON: A Unified Pioneer-Assisted Task RecommendatiON Framework in Realistic Crowdsourcing System. In: Li, Y., Cardei, M., Huang, Y. (eds) Combinatorial Optimization and Applications. COCOA 2019. Lecture Notes in Computer Science(), vol 11949. Springer, Cham. https://doi.org/10.1007/978-3-030-36412-0_45
Download citation
DOI: https://doi.org/10.1007/978-3-030-36412-0_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36411-3
Online ISBN: 978-3-030-36412-0
eBook Packages: Computer ScienceComputer Science (R0)