论文部分内容阅读
随着互联网和信息技术的不断发展,投资者获得相关信息的渠道日益丰富,方式也愈加便捷。互联网的膨胀带来了海量的非结构化数据,如新闻、微博等等,如何利用这些信息从而进一步为投资者提供决策支持成为近年来的研究热点。本文从午间公告新闻类型的角度出发,通过提取关键词与K-Means聚类得到初步的新闻类型,然后利用支持向量机进行新闻的分类预测。最后,我们从事件研究的角度出发探讨了新闻类型对当天下午股票价格的影响。
With the continuous development of the Internet and information technology, investors have become more and more richly-informed and in a more convenient way. The expansion of the Internet has brought massive unstructured data, such as news, microblogging, etc. How to use this information to further provide decision support for investors has become a research hot spot in recent years. In this paper, from the point of view of the type of news announcements at noon, preliminary news types are obtained by extracting key words and K-Means clustering, and then using SVM to forecast news classification. Finally, from the perspective of incident research, we discuss the impact of news types on the afternoon stock prices.