Using machine learning methods, we develop a new measure of aggregate analyst sentiment. We first train analyst-specific neural network (NN) models that capture each analyst's common biases across firms. Using NN model outputs, we decompose the forecast errors of individual analysts into...

We show that the personal traits of analysts, as revealed by their political donations, influence their forecasting behavior and stock prices. Analysts who contribute primarily to the Republican Party adopt a more conservative forecasting style. Their earnings forecast revisions are less likely...

Using Internet search volume for lottery to capture gambling sentiment shifts, we show that when the overall gambling sentiment is high, investor demand for lottery-like stocks increases, these stocks earn positive short-run abnormal returns, managers are more likely to announce stock splits to...

This paper examines how gambling-motivated trading affects aggregate financial market outcomes. Using a unique global gambling data set covering 39 countries, we show that the dollar volume of stock market gambling is at least 3.5 times the combined volume of “traditional” gambling outlets...

This study shows that weather-based indicators of mood impact perceptions of mispricing and trading decisions of institutional investors. Using survey and disaggregated trade data, we show that relatively cloudier days increase perceived overpricing in individual stocks and the Dow Jones...

We investigate whether gambling-motivated retail trading generates mispricing among firms with extreme negative news. Employing a novel accounting-based measure of failure propensity conveyed by the going-concern (GC) audit opinions, we show that gambling-induced trading in GC firms with...

We examine whether exogenous and extremely negative events such as terrorist attacks and mass shootings influence the sentiment and forecasts of sell-side equity analysts. We find that analysts who are local to these attacks issue forecasts that are relatively more pessimistic than the consensus...

We examine whether earnings forecasts of sell-side equity analysts are influenced by the forecasts of other analysts on other firms in the analyst portfolio. We find that analysts exhibit “social learning” where analyst optimism is negatively correlated with the recent forecast errors among...

This paper examines whether sell-side equity analysts use labor market information, as reflected in job postings and corporate layoffs, to improve the quality of their earnings forecasts. We posit that labor market activities contain useful incremental information about the related firm and the...

Using Bloomberg’s daily Twitter Sentiment data for S&P500 firms, we show that Twitter information reduces forecast optimism and improves forecast accuracy of sell-side equity analysts. Negative Twitter information is more influential, and this effect is distinct from the impact of news. Using...