STWM: A Solution to Self-adaptive Task-Worker Matching in Software Crowdsourcing

Fu, Ying; Chen, Haopeng; Song, Feiya

doi:10.1007/978-3-319-27119-4_27

Cited by 8 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, [11] proposed the use of a historical data training classification model to make task assignments based on the similarity between the static attributes needed for the task and the worker's history of completed tasks. Fu et al [12] proposed an extensible metamodel to support the description of a worker's skills and task requirements, and designed an adaptive matching algorithm for task requirements and worker skills to complete task assignment. Mavridis and Gross-Amblard [13] used unstructured tags to simulate skill vectors.…”

Section: Related Workmentioning

confidence: 99%

Software Crowdsourcing Task Allocation Algorithm Based on Dynamic Utility

Wang

Zhou

2019

IEEE Access

View full text Add to dashboard Cite

For crowdsourcing software development, poor matching between the workers' development skills and the requirements for the assigned tasks results in poor quality task completion. In this paper, we propose a dynamic utility task allocation algorithm (DUTA), a software crowdsourcing task allocation algorithm based on the dynamic utility. First, using the attributes provided by the worker registration information, we estimate the initial value of a worker's development abilities based on the attribute weights and levels. Second, the worker's development capabilities are calculated based on his or her history of the completed tasks, including task complexity, quality, and development efficiency. The worker's record of development capability is updated dynamically. Then, based on the skill weights, we calculate the degree to which the task requirements matche the worker's skills. Finally, we take the product of the worker's development ability and the degree of skill matching as the allocation utility, and the total utility is maximized as the optimization goal. To solve the optimal match between tasks and workers, we use the Kuhn-Munkres algorithm with a weighted bipartite graph. Our experimental results showed that DUTA provided good performance in total allocation utility, with a better task allocation success rate than the algorithm based on the user reliability. The DUTA achieved an average allocation accuracy of up to 85.63%, demonstrating that it can guide task assignments effectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Software Crowdsourcing Task Allocation Algorithm Based on Dynamic Utility

Wang

Zhou

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This method can guarantee the quality of the tasks, but the competitive tasks with a long development cycle will cause great loss to the losing candidates. Therefore, this method is only suitable for micro, short-term development tasks, and it is also difficult and time-consuming to select winners from a large number of submitted tasks [14]. The other is based on the bidding mode, such as GetACoder [15], zbj.com, codemart, jointForce, etc.…”

Section: Introductionmentioning

confidence: 99%

Crowdsourcing Software Task Assignment Method for Collaborative Development

Zhou

Wang

2019

IEEE Access

View full text Add to dashboard Cite

Software crowdsourcing is an emerging and promising software development model. It is based on the characteristics of Internet community intelligence, which makes it have certain advantages in development cost and product quality. Companies are increasingly using crowdsourcing to accomplish specific software development tasks. However, this development model still faces many challenges. One of the key issues is the collaboration between crowdsourced workers. Developer collaboration is important to software development, but workers in crowdsourcing come from an undefined network community, so it's hard to guarantee that they can work together. This paper focuses on task assignment and uses the active time of workers as the basis of grouping to provide a solution for multi-task to multi-worker allocation. Based on the on-demand distribution model, this paper considers three factors: worker's ability, task module complexity, and worker's active time. First, the workers are divided into multiple collaborative candidate groups based on active time. Then, the Hungarian algorithm is used to select the optimal workers for each module from the collaborative candidate groups of each task, and the coordination candidate group replacement strategy is used to solve the assignment failure problem. Finally completing the assignment of all tasks within an assignment cycle. The experiments have shown that the proposed method increases the total utility by 25% and the success rate of distribution by 30% than the sequential assignment method. The proposed method can give a reasonable solution for software crowdsourcing task allocation based on collaborative development. INDEX TERMS Crowdsourcing, software development, collaborative candidate group, Hungarian algorithm, active time.

show abstract