Scholars and practitioners alike increasingly recognize the importance of stock microblogs as they capture the market discussion and have predictive value for financial markets. This paper examines the extent to which stock microblog messages are related to financial market indicators and the mechanism leading to efficient aggregation of information. In particular, this paper investigates the information content of stock microblogs with respect to individual stocks and explores the effects of social influences on an interday and intraday basis. We collected more than 1.2 million stock-related messages (i.e., tweets) related to S&P 100 companies over a period of 7 months. Using methods from computational linguistics, we went through an elaborate process of message feature reduction, spam detection, language detection, and slang removal, which has led to an increase in classification accuracy for sentiment analysis. We analyzed the data on both a daily and a 15-min basis and found that the sentiment of messages is positively affected with contemporaneous daily abnormal stock returns and that message volume predicts 15-min follow-up returns, trading volume, and volatility. Disagreement in microblog messages positively influences stock features, both in interday and intraday analysis. Notably, if we give a greater share of voice to microblog messages depending on the social influence of microbloggers, this amplifies the relationship between bullishness and abnormal returns, market volume, and volatility. Following knowledgeable investors advice results in more power in explaining changes in market features. This offers an explanation for the efficient aggregation of information on microblogging platforms. Furthermore, we simulated a set of trading strategies using microblog features and the results suggest that it is possible to exploit market inefficiencies even when transaction costs are included. To our knowledge, this is the first study to comprehensively examine the association between the information content of stock microblogs and intraday stock market features. The insights from the study permit scholars and professionals to reliably identify stock microblog features, which may serve as valuable proxies for market sentiment and permit individual investors to make better investment decisions.

中文翻译：

---

不仅仅是噪音？考察金融市场股票微博的信息内容

学者和从业者都越来越认识到股票微博的重要性，因为它们捕捉市场讨论并对金融市场具有预测价值。本文考察了股票微博消息与金融市场指标的相关程度以及导致信息有效聚合的机制。特别地，本文调查了股票微博关于个股的信息内容，并探讨了社会影响对日间和日内的影响。在 7 个月的时间里，我们收集了超过 120 万条与标准普尔 100 指数公司相关的股票相关信息（即推文）。使用计算语言学的方法，我们经历了消息特征减少、垃圾邮件检测、语言检测和俚语去除的复杂过程，这导致情感分析的分类准确性提高。我们分析了每日和 15 分钟的数据，发现消息的情绪受到同期每日异常股票回报的积极影响，消息量预测 15 分钟的后续回报、交易量和波动性。在日间和日内分析中，微博消息中的分歧对股票特征产生积极影响。值得注意的是，如果我们根据微博博主的社会影响力为微博消息提供更大的发言权，这会放大看涨与异常回报、市场量和波动性之间的关系。遵循知识渊博的投资者的建议会更有力地解释市场特征的变化。这为微博平台上信息的有效聚合提供了解释。此外，我们使用微博功能模拟了一组交易策略，结果表明，即使包含交易成本，也有可能利用市场低效率。据我们所知，这是第一项全面考察股票微博信息内容与股市日内特征之间关联的研究。该研究的见解使学者和专业人士能够可靠地识别股票微博特征，这些特征可以作为市场情绪的宝贵代理，并允许个人投资者做出更好的投资决策。我们使用微博功能模拟了一组交易策略，结果表明，即使包含交易成本，也有可能利用市场低效率。据我们所知，这是第一项全面考察股票微博信息内容与股市日内特征之间关联的研究。该研究的见解使学者和专业人士能够可靠地识别股票微博特征，这些特征可以作为市场情绪的宝贵代理，并允许个人投资者做出更好的投资决策。我们使用微博功能模拟了一组交易策略，结果表明，即使包含交易成本，也有可能利用市场低效率。据我们所知，这是第一项全面考察股票微博信息内容与股市日内特征之间关联的研究。该研究的见解使学者和专业人士能够可靠地识别股票微博特征，这些特征可以作为市场情绪的宝贵代理，并允许个人投资者做出更好的投资决策。