492
Views
13
Downloads
2
Crossref
N/A
WoS
4
Scopus
N/A
CSCD
Allocation of complex crowdsourcing tasks, which typically include heterogeneous attributes such as value, difficulty, skill required, effort required and deadline, is still a challenging open problem. In recent years, agent-based crowdsourcing approaches focusing on recommendations or incentives have emerged to dynamically match workers with diverse characteristics to tasks to achieve high collective productivity. However, existing approaches are mostly designed based on expert knowledge grounded in well-established theoretical frameworks. They often fail to leverage on user-generated data to capture the complex interaction of crowdsourcing participants’ behaviours. This paper aims to address this challenge.
The paper proposes a policy network plus reputation network (PNRN) approach which combines supervised learning and reinforcement learning to imitate human task allocation strategies which beat artificial intelligence strategies in this large-scale empirical study. The proposed approach incorporates a policy network for the selection of task allocation strategies and a reputation network for calculating the trends of worker reputation fluctuations. Then, by iteratively applying the policy network and reputation network, a multi-round allocation strategy is proposed.
PNRN has been trained and evaluated using a large-scale real human task allocation strategy data set derived from the Agile Manager game with close to 500,000 decision records from 1,144 players in over 9,000 game sessions. Extensive experiments demonstrate the validity and efficiency of computational complex crowdsourcing task allocation strategy learned from human participants.
The paper can give a better task allocation strategy in the crowdsourcing systems.
Allocation of complex crowdsourcing tasks, which typically include heterogeneous attributes such as value, difficulty, skill required, effort required and deadline, is still a challenging open problem. In recent years, agent-based crowdsourcing approaches focusing on recommendations or incentives have emerged to dynamically match workers with diverse characteristics to tasks to achieve high collective productivity. However, existing approaches are mostly designed based on expert knowledge grounded in well-established theoretical frameworks. They often fail to leverage on user-generated data to capture the complex interaction of crowdsourcing participants’ behaviours. This paper aims to address this challenge.
The paper proposes a policy network plus reputation network (PNRN) approach which combines supervised learning and reinforcement learning to imitate human task allocation strategies which beat artificial intelligence strategies in this large-scale empirical study. The proposed approach incorporates a policy network for the selection of task allocation strategies and a reputation network for calculating the trends of worker reputation fluctuations. Then, by iteratively applying the policy network and reputation network, a multi-round allocation strategy is proposed.
PNRN has been trained and evaluated using a large-scale real human task allocation strategy data set derived from the Agile Manager game with close to 500,000 decision records from 1,144 players in over 9,000 game sessions. Extensive experiments demonstrate the validity and efficiency of computational complex crowdsourcing task allocation strategy learned from human participants.
The paper can give a better task allocation strategy in the crowdsourcing systems.
Aljanaki, A., Wiering, F. and Veltkamp, R.C. (2016), “Studying emotion induced by music through a crowdsourcing game”, Information Processing & Management, Vol. 52 No. 1, pp. 115-128.
Watkins, C.J.C.H. and Dayan, P. (1992), “Q-learning”, Machine Learning, Vol. 8 Nos 3/4, pp. 279-292.
Galla, T. and Farmer, J.D. (2013), “Complex dynamics in learning complicated games”,Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS’15) (AAMAS’15), Vol. 110 No. 4, pp. 1232-1236.
Goh, A.T.C. (1995), “Back-propagation neural networks for modeling complex systems”, Artificial Intelligence in Engineering, Vol. 9 No. 3, pp. 143-151.
Jøsang, A., Ismail, R. and Boyd, C. (2007), “A survey of trust and reputation systems for online service provision”, Decision Support Systems, Vol. 43 No. 2, pp. 618-644.
Khare, R., Good, B.M., Leaman, R., Su, A.I. and Lu, Z. (2015), “Crowdsourcing in biomedicine: challenges and opportunities”, Briefings in Bioinformatics, Vol. 17 No. 1, pp. 23-32.
LaToza, T.D. and van der Hoek, A. (2016), “Crowdsourcing in software engineering: models, motivations, and challenges”, IEEE Software, Vol. 33 No. 1, pp. 74-80.
Man, Z., Lee, K., Wang, D., Cao, Z. and Miao, C. (2011), “A new robust training algorithm for a class of single-hidden layer feedforward neural networks”, Neurocomputing, Vol. 74 No. 16, pp. 2491-2501.
Miao, C., Yu, H., Shen, Z. and Leung, C. (2016), “Balancing quality and budget considerations in mobile crowdsourcing”, Decision Support Systems, Vol. 90, pp. 56-64.
Yu, H., Shen, Z., Miao, C., Leung, C., Chen, Y., Fauvel, S., Lin, J., Cui, L., Pan, Z. and Yang, Q. (2017), “A dataset of human decision-making in teamwork management”, Scientific Data, Vol. 4, p. 160127.
This work is partially supported by NSFC (No.61572295), the Innovation Method Fund of China(No.2015IM010200), SDNSFC (No. ZR2014FM031), the TaiShan Industrial Experts Programme of Shandong Province, the Shandong Province Science and Technology Major Special Project(No.2015ZDXX0201B03, 2015ZDXX0201A04, 2015ZDJQ01002), the Shandong Province Key Research and Development Plan (No.2015GGX101015, 2015GGX101007).
Lizhen Cui, Xudong Zhao, Lei Liu, Han Yu and Yuan Miao. Published in International Journal of Crowd Science. Published by Emerald Publishing Limited. This article is published under the Creative Commons Attribution (CC BY 4.0) licence. Anyone may reproduce, distribute, translate and create derivative works of this article (for both commercial and non-commercial purposes), subject to full attribution to the original publication and authors. The full terms of this licence may be seen at http://creativecommons.org/licences/by/4.0/legalcode