面向评论语义关系的学术APP服务需求聚合研究

[目的/意义]文章提出一种从海量非结构化评论数据中聚合用户对学术APP服务需求的思路与方法,为平台的开发者及运营者高效挖掘并分析用户需求提供指导。[方法/过程]以学术APP用户评论为研究对象,在Word2vec词向量表达的基础上,提出一种基于Canopy-Kmeans和MMR的服务需求聚合方法。并以丁香园APP用户评论为样本,利用Python 3. 7与Matlab R2016a完成实验过程。[结果/结论]实验结果表明文章提出的技术方法能够有效识别并聚合学术APP的服务需求,为大数据环境下从数据层面挖掘用户需求提供参考借鉴。

Research on the Aggregation of Academic APP Service Demands Oriented to Semantic Relationship of Comments

[Purpose/significance] This paper proposes an idea and method to aggregate users’ demand for academic application service from massive unstructured comment data,so as to provide guidance for developers and operators of the platform to efficiently mine and analyze users’ demand. [Method/process] Taking academic application user comments as the research object,On the basis of the word vector expression according to Word2 vec,proposing a service demand aggregation method based on Canopy-Kmeans and MMR. In addition,taking the data of Ding xiangyuan application user comments as sample,using Python 3. 7 and Matlab R2016 a to complete the experiment. [Result/conclusion]The experimental results show that the technical method proposed in this paper can effectively identify and aggregate the service requirements of academic application. It provides a reference for mining user needs from the data level under the big data environment.