摘要
论文探讨利用R语言工具对图书馆新浪微博数据进行子主题聚类和挖掘,指出:在文本分词、构建词频——文档矩阵的基础上,使用Pamk算法和Kmeans算法进行微博聚类,获取图书馆服务质量评价与建议信息,挖掘图书馆核心微博用户,便于图书馆利用微博数据评估服务效果,改进服务质量。
This paper investigates the sub topic mining and clustering of the library's Sina microblog data by using R language tool. It points out that based on the text segmentation and term-document matrix, clustering library's Sina microblog data by using Pamk algorithm and Kmeans algorithm to gain library's service quality evaluations and advices and to unearth Sina microblog's core?users of the library, can be easy for us to evaluate the library's service effect and improve its service quality.
出处
《新世纪图书馆》
CSSCI
2014年第8期20-23,共4页
New Century Library
关键词
微博
图书馆服务质量评价
文本聚类
核心用户
Microblog. Library's service quality evaluation. Text clustering. Core users.