Extracting sentiment from text is a hard semantic problem. We develop a methodology for extracting small investor sentiment from stock message boards. The algorithm comprises different classifier algorithms coupled together by a voting scheme. Accuracy levels are similar to widely used Bayes classifiers, but false positives are lower and sentiment accuracy higher. Time series and cross-sectional aggregation of message information improves the quality of the resultant sentiment index, particularly in the presence of slang and ambiguity. Empirical applications evidence a relationship with stock values--tech-sector postings are related to stock index levels, and to volumes and volatility. The algorithms may be used to assess the impact on investor opinion of management announcements, press releases, third-party news, and regulatory changes.text classification, index formation, computers-computer science, artificial intelligence, finance, investment

Common Failings: How Corporate Defaults are CorrelatedWe develop, and apply to data on U.S. corporations from 1979-2004, tests of the standard doubly-stochastic assumption under which firms' default times are correlated only as implied by the correlation of factors determining their default intensities. This assumption is violated in the presence of contagion or "frailty" (unobservable explanatory variables that are correlated across firms). Our tests do not depend on the time-series properties of default intensities. The data do not support the joint hypothesis of well specified default intensities and the doubly-stochastic assumption. There is also some evidence of default clustering in excess of that implied by the doubly-stochastic model with the given intensities.How corporate defaults are correlated 1

No abstract

No abstract

No abstract