Deep learning-based recommendation method for top-K tasks in software crowdsourcing systems

Abstract

The task personalized recommendation problems in software crowdsourcing systems have unique characteristics, i.e., large task flow, high task complexity, long development cycle, winning task competitions, professional ability requirements, etc. However, existing software crowdsourcing recommendation mechanisms do not consider the contextual information of crowdsourcing tasks. In particular, the effects of crowdsourcing workers' interest changes and capability constraints on task selection are usually ignored. Therefore, this study proposes a new worker capability-correction long- and short-term attention network (CLSAN) recommendation framework. Firstly, explicit and implicit features are obtained from the feature data of crowdsourcing workers and historical crowdsourcing tasks. The long-term and short-term feature layers are extracted by adding LSTM to the historical tasks; the attention weight of user preference is calculated by integrating the attention mechanism to obtain each user's personalized preference. Secondly, this study considers that the capabilities of the worker need to be matched with the skills required for the software task. We design a worker capability correction model that uses Word2Vec software to obtain competency similarities between crowdsourcing workers and tasks, thereby determining the priority of tasks that satisfy the worker's capability. The experimental results show that CLSAN can accurately evaluate the changes of interest preferences of crowdsourcing workers, and effectively improve the quality and efficiency of crowdsourcing recommendations.