Agenda

David Ardia - University of Neuchâtel

Media Abnormal Tone, Returns, and Earnings Announcements 
Abstract - We introduce the Cumulative Abnormal Tone (CAT) event study methodology for tracking the dynamics of abnormal textual tone about an aspect of an entity around the time of events. To compute the textual tone, we recommend the Generalized Word Power method, which uses regression techniques to estimate the polarity of the words belonging to a pre-defined lexicon. We apply the CAT event study and Generalized Word Power methodologies to media reports about firms' future performance published around the time of quarterly earnings announcements of non- financial S&P 500 firms over the period 2000-2016. We find that the abnormal tone is more sensitive to negative earnings surprises than positive ones. Additionally, we report that investor overreact to the abnormal tone contribution of web publications at earnings announcement date, which generate a stock price reversal in the following month.

Questioning the News About Economic Growth: Sparse Forecasting Using Thousands of News-Based Sentiment Values
Abstract - Modern calculation of textual sentiment involves a myriad of choices for the actual calibration. We introduce a general sentiment engineering framework that optimizes the design for forecasting purposes. It includes the use of the elastic net for sparse data-driven selection and weighting of thousands of sentiment values. These values are obtained by pooling the textual sentiment values across publication venues, article topics, sentiment construction methods, and time. We apply the framework to investigate the added value of textual analysis-based sentiment indices for forecasting economic growth in the US. We find that, compared to the use of high-dimensional forecasting techniques based on only economic and financial indicators, the additional use of optimized news-based sentiment values yields significant accuracy gains in forecasting the nine-month and annual growth rates of the US industrial production.