Mitigating Herding in Hierarchical Crowdsourcing Networks.

Han Yu,Yiqiang Chen,Qiang Yang,Chunyan Miao,Simon Fauvel,Victor R Lesser,Cyril Leung

doi:10.1038/s41598-016-0011-6

Abstract

Hierarchical crowdsourcing networks (HCNs) provide a useful mechanism for social mobilization. However, spontaneous evolution of the complex resource allocation dynamics can lead to undesirable herding behaviours in which a small group of reputable workers are overloaded while leaving other workers idle. Existing herding control mechanisms designed for typical crowdsourcing systems are not effective in HCNs. In order to bridge this gap, we investigate the herding dynamics in HCNs and propose a Lyapunov optimization based decision support approach - the Reputation-aware Task Sub-delegation approach with dynamic worker effort Pricing (RTS-P) - with objective functions aiming to achieve superlinear time-averaged collective productivity in an HCN. By considering the workers’ current reputation, workload, eagerness to work, and trust relationships, RTS-P provides a systematic approach to mitigate herding by helping workers make joint decisions on task sub-delegation, task acceptance, and effort pricing in a distributed manner. It is an individual-level decision support approach which results in the emergence of productive and robust collective patterns in HCNs. High resolution simulations demonstrate that RTS-P mitigates herding more effectively than state-of-the-art approaches.

Highlights

The organization of social and economic activities to efficiently coordinate participants’ effort is an important topic of economic theory
In our previous work[18], we have proved that the joint task acceptance and sub-delegation decisions made under prices of service fixed by the crowdsourcers are asymptotically optimal compared to an oracle that knows the exact situation of each worker at all times
To evaluate the performance of RTS-P under realistic settings, it is compared with four state-of-the-art approaches through extensive numerical experiments in an Hierarchical crowdsourcing networks (HCNs) based on the Epinions trust network dataset[26]

Summary

Introduction

The organization of social and economic activities to efficiently coordinate participants’ effort is an important topic of economic theory. Crowdsourcing communities based around social networks tend to have hierarchical structures[2,3] These hierarchical crowdsourcing networks (HCNs) have been used to mobilize the masses in many significant real-world applications including political rallies[4], scientific research[5], mapping out natural environment features[6,7], and large-scale search-and-rescue missions[8]. Crowdsourcers are typically self-interested; their primary intention is to maximize their own utilities This will usually lead them to only select workers with high perceived reputation, leading to the emergence of herding[9]. It is difficult for a worker to quantify when sub-delegation is needed and who the suitable candidates for sub-delegation are This is further complicated by the fact that different workers may incur different costs to complete the same task. Sub-delegation to a worker resulting in a loss for the sub-delegator is not a rational choice

Methods

Results

Conclusion