融合关联规则的 MOOC 资源众包平台任务分配算法-《计算机技术与发展》

文章信息/Info

Title:: Task Allocation Algorithm in MOOC Resource Crowdsourcing Platform Combined with Association Rules

Author(s):: PAN Zhi-hong¹; WAN Zhi-ping¹; XIE Hai-ming²; 1.Xinhua College of Sun Yat-sen University,Guangzhou 510520,China; 2.China Mobile Group Guangdong Co.,Ltd.,Guangzhou 510623,China

Keywords:: knowledge-intensive crowdsourcing task; MOOC resource construction; task assignment; association rules; Apriori algorithm; expected work ability assessmen

摘要:: 在高校大力发展MOOC平台背景下,为了提升学生的主动性、MOOC平台资源库的丰富性,出现了众包协同构建资源的方法,让学生和教师构成学习共同体,在完成新知识学习的同时进行资源库建设。高校MOOC众包平台的任务就属于知识密集型任务,挑选合适的参与者直接关系到MOOC资源库构建质量。为了更好地构建高校MOOC资源平台,提出一种针对知识密集型众包任务的分配方案,它包含学生的准入筛选、预期工作能力评估两个阶段。首先利用改进 Apriori课程关联算法对学生进行准入筛选;其次利用知识关联算法对学生预期工作能力进行评估并将众包任务分配到工作能力最合适的学生;最后对方案进行测试验证,结果表明该方案能够能较好地提升学生挑选和任务分配的效果,促进构建更高质量的MOOC资源库。

Abstract:: In the context of vigorously developing MOOC platform in colleges and universities,in order to enhance the initiative of students and the richness of the MOOC platform resource,there is a crowdsourcing method for collaboratively building resources,which enables students and teachers to form a learning community and carry out the resource construction while learning the new knowledge. Since the task of college MOOC crowdsourcing platform is knowledge-intensive,the selection of appropriate participants is directly related to the construction quality of MOOC resource pool. In order to better build an excellent resource pool for college MOOC platform,we propose a task allocation scheme for knowledge-intensive crowdsourcing task,which includes two stages of student admission screening and expected work ability assessment. Firstly the course association rules based on improved Apriori algorithm are used to make the student admission judgment. Secondly,the knowledge association rules are used to evaluate the students’ ability and assign the crowdsourcing tasks to students with the most appropriate work ability. Finally,the performance of the proposed scheme is tested and verified. The results show that it can improve the effect of student selection and task assignment,and promote the construction of higher quality MOOC resources.