基于用户适用度的开放数据质量提升研究  

The Research of Improving Open Data Quality Based on Fitness for Use

作　　者：王瑞云[1] 贾君枝 WANG RuiYun;JIA JunZhi(School of Economics and Management, Shanxi University, Taiyuan 030006, China;School of Information Resources Management, Renmin University of China, Beijing 100872, China)

机构地区：[1]山西大学经济与管理学院,太原030006 [2]中国人民大学信息资源管理学院,北京100872

出　　处：《数字图书馆论坛》2018年第12期18-26,共9页Digital Library Forum

基　　金：国家社会科学基金重点项目"基于关联数据的中文名称规范档语义描述及数据聚合研究"(编号:15ATQ004)资助

摘　　要：本文研究如何提高开放数据质量以更好地满足用户的应用需求。先分析用户需求匹配的行为过程,以北京开放数据门户网站的个体数据集为基本研究对象,选取浏览次数、下载次数和下载浏览比作为外部行为结果指标;然后分析外部指标与数据集的主题、元数据说明、及时性,以及数据表列数、行数等内在质量指标的可能的正相关关系;从相关分析中发现极端不符合正相关的异常数据集,联系这些数据集的用户选择情景深入讨论,提出针对这些异常数据集的质量提升建议。This paper aims at improving open data quality on fitness for use. Exploring behaviors of users’ demand matching, using bjdata.gov.cn as study case, selecting downloads, reviews of every dataset and their express computing as output indices, we research the possibility of positive relationship of between above indices and other dataset’s inner quality indices which containing content theme, metadata, timeliness, columns and rows of data resource table. More importantly we find out many exceptional datasets that don’t extremely confirm to the positive relationship, and discuss further those datasets on their user selection context. Finally we suggest on quality improving for those exception datasets.

关 键 词：开放数据质量 用户适用度 需求匹配 下载浏览比 

分 类 号：G254[文化科学—图书馆学]