"Let me get back to you" - A machine learning approach to measuring non-answers

It is relatively easy for us humans to detect when a question we asked has not been answered - we teach this skill to a computer. Using a supervised machine learning framework on a large training set of questions and answers, we identify 1,027 trigrams that signal non-answers. We show that this glossary has economic relevance by applying it to contemporaneous stock market reactions after earnings conference calls. Our findings suggest that obstructing the flow of information leads to significantly lower cumulative abnormal stock returns and higher implied volatility. Our metric is designed to be of general applicability for Q&A situations, and hence, is capable of identifying non-answers outside the contextual domain of financial earnings conference calls