26
开发商业智能应用
小 心大 数 据“陷 阱”
黄锦辉
香港中文大学工程学院,香港 999077
摘要
大数据的应用和研究是信息爆炸时代的热点话题。就如何更智能地发现大数据中的有用信息展开讨论,
探讨了大数据中的“陷阱”和其引发的社会危害,提出一种面向社交文本的智能应用系统,以有效规避大
数据中的“陷阱”并自动提取有用信息;基于提到的框架,展示了笔者研究组近些年在社交媒体上的事件
检测、自动摘要和谣言检测方面的研究成果。
关键词
大数据;自然语言处理;社交媒体;数据处理
中图分类号:TP391 文献标识码:A
doi: 10.11959/j.issn.2096-0271.2017016
Beware of traps of big data analytics in business
WONG Kam Fai
Faculty of Engineering, The Chinese University of Hong Kong, Hong Kong 999077, China
Abstract
In the era of data explosion, research and application of big data has become a hot topic. How to automatically
discover useful information from big data was focused. The organization is as following: examples of big data
“traps” and their influences were discussed. The framework of an intelligent system to process social media texts
that avoids traps and extracts useful information from big data was described. The research works proposed by
our team and based on the framework about event detection, summarization and rumor detection were covered.
Key words
big data, natural language processing, social media, data processing
2016016-262017016-1