Is All That Talk Just Noise? The Information Content of Internet Stock Message Boards

By Werner Antweiler, Murray Z. Frank. 2004

2,313 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Finance

Citations in the corpus

Textual Sentiment in Finance: A Survey of Methods and Models (2014, methodology): “Antweiler and Frank (2004) use the default method Naïve Bayesian algorithm within the Rainbow package to classify messages into one of three categories: buy, sell and hold.”
Good debt or bad debt: Detecting semantic orientations in economic texts (2013, background): “To the best of our knowledge, only a handful of studies have chosen to use statistical or machine learning techniques for ﬁnancial sentiment analysis (Antweiler & Frank, 2004; Das & Chen, 2007; Li, 2009; O’Hare et al., 2009).”
Retail investor attention and stock price crash risk: Evidence from China (2019, background): “, Antweiler and Frank (2004), Das and Chen (2007), Kim and Kim (2014), and Bajo et al.”
Machine Learning: An Applied Econometric Approach (2017, background): “Antweiler and Frank (2004) classify text on online financial message boards as bullish, bearish, or neither.”
Soft information in earnings announcements: news or noise? (2008, methodology): “…word counts as in Li (2006); researcher-designed automated scoring programs as in Lucca and Trebbi (2008) or Bayesian-updating methods as in Antweiler and Frank (2004) and Li (2008); the development of optimism (or “bullishness”) indices based upon multiple underlying language processing…”
customers as advisors: the role of social media in financial markets (2011, neutral): “The average length of an SA article is 489 words, which is comparable to the average length of a WSJ article (482 words) and significantly longer than that of an average message posted on Internet message boards or forums (which, according to Antweiler and Frank (2004), is between 20 and 50 words).”
The effect of news and public mood on stock movements (2014, background): “Frank and Antweiler [15] Bullish, bearish General emotion General market NA Real value, trend NB algorithm”
A survey of the applications of text mining in financial domain (2016, background): “Antweiler and Frank (2004) presented a study on stock message boards.”
Information Demand and Stock Market Volatility (2012, background): “This approach recognizes the fact that the internet has nowadays revolutionized the production, intermediation, dissemination and consumption of information in the financial industry (see Barber and Odean, 2001; Antweiler and Frank, 2004; Rubin and Rubin, 2010).”
News-based trading strategies (2016, methodology): “While previous research [11, 12, 13, 14] succeeded in establishing a link between news tone and stock market prices, it was not clear how the extracted sentiment signals could then be utilized to facilitate investment decisions.”
Applications of news analytics in finance: A review (2012, methodology): “This is consistent with Antweiler and Frank (2004). Trading volume and volatility are strongly related to each other.”
Tensor-Based Learning for Predicting Stock Movements (2015, neutral): “…and Titman 1993), whereas modern behavioral finance is interested in the shortterm shock of sentimental factors and event-specific factors (Bollen, Pepe, and Mao 2011; Frank and Antweiler 2004; Gilbert and Karahalios 2010; Schumaker and Chen 2009b; Tetlock, Saar-Tsechansky, and Macskassy 2008).”
More than Words: Quantifying Language to Measure Firms' Fundamentals (2008, background): “For example, Antweiler and Frank (2004) and Das and Chen (2006) design algorithms to reproduce human beings’ “bullish,” “neutral,” or “bearish” ratings of internet chat room messages and news stories.”