How are social and mass media different in relation to the stock market? A study on topic coverage and predictive value

How are social and mass media different in relation to the stock market? A study on topic coverage and predictive value
复制标题

DOI:
10.1016/j.im.2021.103588
复制
发表时间:
2021-12
期刊:
Inf. Manag.
影响因子:
--
通讯作者:
Hang Dong-;J. Ren;B. Padmanabhan;J. Nickerson
Hang Dong-;J. Ren;B. Padmanabhan;J. Nickerson
中科院分区:
其他
文献类型:
--
作者:
Hang Dong-;J. Ren;B. Padmanabhan;J. Nickerson

文献摘要

被引文献

相似文献

尽管金融市场的投资者可以从大众媒体和社交媒体获取信息,但策划和提供这些信息的交易平台在理解这两种媒体之间的差异方面几乎没有什么可借鉴的。本文将社交媒体与股票市场中的大众媒体进行比较,重点关注信息覆盖多样性和对未来股票绝对回报的预测价值。根据对新浪财经新闻平台近百万条股票相关新闻文章和中国热门微博平台1270万条股票相关社交媒体消息的研究,我们发现社交媒体对股票的报道少于大众媒体,而且这种效应随着媒体信息量的增加而放大。我们发现这些来源有一些短期预测价值,但它们是不同的。尽管大众媒体信息报道在一日范围内比社交媒体信息报道更具预测性,但在两到五天范围内却相反。这些实证结果表明,社交媒体和大众媒体为股市投资者提供的服务不同。我们将与群体和专家之间差异相关的理论联系起来,并为媒体相关信息系统的设计提供实际意义。
Although investors in financial markets have access to information from both mass media and social media, trading platforms that curate and provide this information have little to go by in terms of understanding the difference between these two types of media. This paper compares social media with mass media in the stock market, focusing on information coverage diversity and predictive value with respect to future stock absolute returns. Based on a study of nearly a million stock-related news articles from the Sina Finance news platform and 12.7 million stock-related social media messages from the popular Weibo platform in China, we find that social media covers less stocks than mass media, and this effect is amplified as the volume of media information increases. We find that there is some short-term predictive value from these sources, but they are different. Although mass media information coverage is more predictive than social media information coverage in a one-day horizon, it is the other way around in a two-to five-day horizon. These empirical results suggest that social media and mass media serve stock market investors differently. We draw connections to theories related to how crowds and experts differ and offer practical implications for the design of media-related IS systems.