We examine the information sweep along for four stocks over seven month to trace the relationship between on-line discussion.

We examine the information sweep along for four stocks over seven month to trace the relationship between on-line discussion, of recent origins activity, and stock price emotions On-line discussions support numerous unsubstantiated rumors, substantial on-point exchanges, and quick dissemination of imminent and not long ago released information. Applying language-processing routines to message board postings and recently made knowns we create sentiment and disagreement measures or "eInformation." We analyze the determinants of sentiment and disagreement, and trace links between freshs eInformation, and stock returns. This intensive clinical meditation of on-line discussions suggests mechanisms individual investors and form into groupss can use to analyze and digest company information.

**********

In light of the large visible form [i]or[/i] frame of research on informationally efficient markets, there pretends little left to learn from the continued empirical examination of information and markets. It would be seen similarly pointless for individual investors to make experiment of to compete with professional analysts. However, understanding the individuals' investing decisions has been common of the most vibrant research streams in fresh years (see Roll, 1986, Odean, 1998 Gervais and Odean, 2001 and Barber and Odean, 2001)

Technology, in the form of stock chat message boards, now provides a of the present day real-time window into discussions by way of individual investors. It is instructive to peek by the agency of this window to observe for what reason information is digested, how sentiment unrolls and how perceptions are related to prices.

The arrangement we adopt in this article is to use a clinical, i.e., small sample, approach to understanding investor behavior. Before framing hypotheses or constructing criterions it is important to establish a base horizontal of understanding in an area. Thus, our article is decidedly descriptive, part of a in extent inductive tradition in economics (Blaug, 1992) We do not attempt to either affirm or throw aside theory. Rather, we suggest a series of working hypothesiss (or hypotheses) that can be bring outed through subsequent model building and large-scale empirical study

We have three goals in this article. First, we closely analyze the the bulk of mankind who share their opinions (posters) and their discussions surrounding a not many stocks. Given the anonymous nature of this activity, we instead fix upon to study an outlier at interviewing an extensive poster. Doing to such a degree enables us to understand to what end someone would spend substantial amounts of time posting messages to united of the boards we study

As part of our analysis, we also focus attention upon the discussions themselves. Although there is a perception that postings are "garbage," to the contrary, discussions sustain on-point exchanges, generate possibly non-public information, quickly disseminate public information from recents stories, and serve as forums where investors can extract meaning from information. Chat swings and postings are also sources of numerous unsubstantiated rumors, adding noise to the information roll on Nevertheless, the fact that unruffled some nonpublic information may be released onward the boards--and the observation that placards use the boards to proof their own analyses and obtain those of others--may explain for what cause [i]or[/i] reason posters and surfers continue to every-day these chat board sites.

next to the first using language-processing algorithms, we measure the intensity and dispersion of sentiment (which we entitle eInformation) for over 170,000 messages pillared about four stocks. We analyze the determinants of the of the same height of sentiment and disagreement among hand-bills and find that there is a bring to a period relationship between sentiment levels, stock prices, and trading bulk We also find that disagreement is related to the intensity of discussion.

Finally, we explore the usefulness of denoteed investor sentiment (eInformation) to predict stock recurs Our clinical study confirms other studies that fail to find predictive power forecasting replys (Antweiler and Frank, 2002, 2004 and Das and Chen, 2003)

The article take stepss as follows. Section I deals with our clinical design. In Section II, we discuss the demographics of [i]affiche[/i]s detailing our interview with an especially active investor-discussant. Section III reports upon our clinical examination of the nature of the discussions and the quality of information in those discussions. Section IV describes our computer-generated measures of sentiment and disagreement (eInformation) that are extracted using language-processing algorithms. In Section V we analyze the determinants of our eInformation measures. In Section VI, we examine the relationship of eInformation to the price formation proces Finally, in Section VIII, we summarize the hypotheses that appear from this clinical investigation.

I. Sample Design

We thought four firms over a period of seven month We use these four firms as archetypes for different information environments where traditional and strange eInformation flows vary. As befits a clinical application of mind we attempt to dig profoundly into these four firms, using our observations to derive hypotheses for large-scale studies. We have deliberately not fix uponed pathological examples where posters have used stock message boards to explicitly manipulate prices (Leinweber and Madhavan, 2001)