Preference-aware Task Assignment in Spatial Crowdsourcing: from Individuals to Groups

Zhao, Yan; Zheng, Kai; Yin, Hongzhi; Liu, Guanfeng; Fang, Junhua; Zhou, Xiaofang

doi:10.1109/tkde.2020.3021028

Cited by 30 publications

(15 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Task assignment A significant line of work (Ho and Vaughan 2012;Ho, Jabbari, and Vaughan 2013;Zhao et al 2020) studies the optimal task assignment when tasks are heterogeneous. As optimal task assignment is out of the scope of this paper, during training and testing, our framework samples a specified amount of tasks uniformly randomly from all available tasks.…”

Section: Methodsmentioning

confidence: 99%

Incentivizing an Unknown Crowd

Dong¹,

Li²,

Wang³

2021

Preprint

View full text Add to dashboard Cite

Motivated by the common strategic activities in crowdsourcing labeling, we study the problem of sequential eliciting information without verification (EIWV) for workers with a heterogeneous and unknown crowd. We propose a reinforcement learning-based approach that is effective against a wide range of settings including potential irrationality and collusion among workers. With the aid of a costly oracle and the inference method, our approach dynamically decides the oracle calls and gains robustness even under the presence of frequent collusion activities. Extensive experiments show the advantage of our approach. Our results also present the first comprehensive experiments of EIWV on large-scale real datasets and the first thorough study of the effects of environmental variables.

show abstract

Section: Methodsmentioning

confidence: 99%

Incentivizing an Unknown Crowd

Dong¹,

Li²,

Wang³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The IA algorithm fails to consider travel costs between the locations of workers and tasks. Workers are more likely to perform nearby tasks [1], [19], and travel cost is a critical factor when workers choose which tasks to perform. We compute the travel cost between a worker w i and a task s j , denoted as d(w i .l, s j .l), using Euclidean distance.…”

Section: Distance-based Influence-aware Assignment (Dia)mentioning

confidence: 99%

“…This is common practice when evaluating SC platforms [3], [13], [39], [40]. Since BK does not contain category information of venues, we exact categories of the venues with the aid of the FourSquare API 1 We assume that all users are workers since users who check in at different spots are good candidates to perform nearby spatial tasks, and we assume that their locations are those of the most recent check-ins. Moreover, we set the time granularity to one day, during which the available tasks and workers are entered into our framework.…”

Section: A Experimental Setupmentioning

confidence: 99%

“…With the near-ubiquitous diffusion of smartphones and similar devices, a new kind of crowdsourcing has emerged, namely Spatial Crowdsourcing (SC), where smartphone users serve as workers that perform tasks at specific physical locations. In SC, examples of spatial tasks include reporting local hot spots, taking photos or videos of a POI, and monitoring traffic conditions [1].…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, it is important to infer task execution behaviors based on historical task-performing records of workers. Several approaches use past task-performing patterns to deduce worker preferences for tasks [1], [18], but they do not analyze the willingness of workers to perform tasks, i.e., the probabilities that workers will visit the task locations. If a worker previously performed tasks near a new task, the worker is more likely to visit the location of the new task [19].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Influence-aware Task Assignment in Spatial Crowdsourcing (Technical Report)

Chen¹,

Yan²,

Zheng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

With the widespread diffusion of smartphones, Spatial Crowdsourcing (SC), which aims to assign spatial tasks to mobile workers, has drawn increasing attention in both academia and industry. One of the major issues is how to best assign tasks to workers. Given a worker and a task, the worker will choose to accept the task based on her affinity towards the task, and the worker can propagate the information of the task to attract more workers to perform it. These factors can be measured as worker-task influence. Since workers' affinities towards tasks are different and task issuers may ask workers who performed tasks to propagate the information of tasks to attract more workers to perform them, it is important to analyze worker-task influence when making assignments. We propose and solve a novel influence-aware task assignment problem in SC, where tasks are assigned to workers in a manner that achieves high worker-task influence. In particular, we aim to maximize the number of assigned tasks and worker-task influence. To solve the problem, we first determine workers' affinities towards tasks by identifying workers' historical task-performing patterns. Next, a Historical Acceptance approach is developed to measure workers' willingness of performing a task, i.e., the probability of workers visiting the location of the task when they are informed. Next, we propose a Random reverse reachable-based Propagation Optimization algorithm that exploits reverse reachable sets to calculate the probability of workers being informed about tasks in a social network. Based on worker-task influence derived from the above three factors, we propose three influence-aware task assignment algorithms that aim to maximize the number of assigned tasks and worker-task influence. Extensive experiments on two real-world datasets offer detailed insight into the effectiveness of our solutions.

show abstract

Reward optimization of spatial crowdsourcing for coalition‐based maintenance task

Hao

Zheng

Yang

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Spatial crowdsourcing (SC) can use the moving workers to achieve location‐based tasks. It has been widely used in takeout, data labeling, organizing activities, security and artificial intelligence. Currently, many manufacturers wish to explore SC in maintenance business, as SC can reduce maintenance time, reduce labor costs, and improve customer satisfaction. In maintenance business scenarios, there are two kinds of cooperated participators. One is freedom workers who are sensitive to distance, and the other is employed by manufacturers who are insensitive to distance. Therefore, some methods of SC with one type worker are challenging to apply to maintenance business scenarios directly. To match this scenario, we model the maintenance scenario and prove that this scenario is an NP‐hard problem; then, both greedy and Nash equilibrium methods are proposed to complete the tasks for making a high total reward. The greedy algorithm (GA) first assigns the nearest available workers to each task, and the employee will try to join the task to help GM to complete more tasks, on the condition that the task cannot be completed and reaches a particular proportion. The Nash equilibrium algorithm (NA) is used to find a Nash equilibrium for all the workers and employees. The experiments demonstrate the efficiency and effectiveness of the synthetic data set of gMission in small and large data sets. The finished task number of NA is about 5% more than that of GA, and the reward of NA is about 10% more than that of GA.

show abstract

Preference-aware Task Assignment in Spatial Crowdsourcing: from Individuals to Groups

Cited by 30 publications

References 49 publications

Incentivizing an Unknown Crowd

Incentivizing an Unknown Crowd

Influence-aware Task Assignment in Spatial Crowdsourcing (Technical Report)

Reward optimization of spatial crowdsourcing for coalition‐based maintenance task

Contact Info

Product

Resources

About