【摘要】 众包平台的信息过载使工人面临任务选择的困难.针对众包特征,本研究提出一种考虑工人兴趣和能力的任务推荐方法.该方法基于协同过滤推荐思想,首先通过TF-IDF技术构建考虑兴趣偏好的工人模型,然后将基于胜任力理论分析构建的工人KSAO能力集合融入到模型中,构建新的工人模型;在此基础上,利用余弦相似性、Jaccard相似性和改进的余弦相似性公式,计算工人间融合兴趣和能力的综合相似度,依此来选取近邻集并最终生成推荐.利用猪八戒网采集的数据进行实验,结果表明该方法的有效性,并通过对比实验证实该方法比传统协同过滤方法推荐效果更佳.从推荐视角丰富众包任务选择的研究,对于众包中解决信息过载、增进个性化体验等具有一定的现实意义.更多还原

【Abstract】 Information overload of crowdsourcing systems makes workers facing task selection problem.According to the characteristics of crowdsourcing, the study puts forward a method of task recommendation based on the workers’ interest and competency. On the basis of collaborative filtering recommendation, this method firstly builds the worker model based on workers’ interest through using the TF-IDF scheme, and builds the new worker model by integrating KSAO competency set on the basis of the theory of competency analysis into the above worker model; According to the new worker model, this paper calculates the comprehensive similarity integrated interest with competency by Cosine similarity, Jaccard similarity and improved Cosine similarity, and then finds the nearest neighbors for target workers and finally makes the recommendation. Finally, using real data from the website of ZBJ to experiment, the results showed the effectiveness of the method, and through the contrast experiment proved that this method is better than traditional collaborative filtering method. This paper enriched the task selection study of crowdsourcing from the perspectives of recommendation, and has a certain practical significance of solving information overload, enhancing personalized experience and so on for crowdsourcing.更多还原