【摘要】 通过大数据技术对海量的用户贡献内容构建数据分析系统框架,以酒店为例,进行多维度分析及可视化应用。基于TripAdvisor网站的列表和点评信息,通过分布式爬虫框架爬取所需的数据,经过数据预处理,采用分布式文件系统存储数据,在此基础上运用统计建模及自然语言处理方法进行数据分析研究,借助第三方框架对分析结果进行可视化。研究者在使用该框架时,可以根据自身需求从多个维度进行数据分析及可视化应用。该框架能够有效地对旅游评论大数据进行多维度的统计分析,进而为旅游相关人员提供基于旅游评论大数据的参考信息。更多还原

【Abstract】 This study aims to establish a multi-dimensional data analysis and visualization framework based on traveller review and uses a case study to apply our data analysis and visualization framework. A distributed crawler framework was developed to craw data. A preprocessing method was applied to improve data quality. A distributed file system was used to store data. Based on massive review data,some models were built and nature language process methods were applied for data analysis. At last, the result data was visualized using third-party visualization framework. Users could analyse and visualize traveller review data from multiple dimensions,as well as find valuable information. This framework can analyse and visualize traveller review data from multiple dimensions and help tourism-related personnel find valuable information from big data.更多还原