Crowdsourcing User Community Division and Experimental Analysis Based on Attribute Heterogeneity
Tingting Zhang, Ke Chen, Yuanxing Zhao, Huangtao Zhao · Advances in Computer and Communication · 2024
Under the crowdsourcing environment, dividing the user community is not only beneficial for understanding the platform's user structure and managing resources within the platform but also enhances user group recommendations. In this paper, a comprehensive similarity calculation method based on heterogeneous attributes is proposed, building on existing research and considering the heterogeneity of user attributes and inter-user structure. Based on the similarity between nodes, a specific threshold is selected for community division using a systematic clustering approach. The community structure evaluation function is designed to assess the quality of community division, and the algorithm's accuracy is demonstrated through experimental analysis. The research results show that the method in this paper can not only effectively mine the actual structure within the user community and achieve the rational subgrouping of crowdsourcing users but also help enhance the accuracy of the platform's task recommendations, thereby improving the platform's operational efficiency and visibility.