"Let me get back to you" - A machine learning approach to measuring non-answers
45 Pages Posted: 4 May 2020 Last revised: 20 Jul 2021
Date Written: June 6, 2020
It is relatively easy for us humans to detect when a question we asked has not been answered – we aim to teach this skill to a computer. Using a supervised machine learning framework on a large training set of questions and answers, we identify 1,364 trigrams that signal non-answers in earnings call Q&A. We show that this glossary has economic relevance by applying it to contemporaneous stock market reactions after earnings calls. Our findings suggest that obstructing the flow of information leads to significantly lower cumulative abnormal stock returns and higher implied volatility. As both our method and glossary are free of financial context, we believe that the measure is applicable to other fields with a Q&A setup outside the contextual domain of financial earnings conference calls.
Keywords: Econlinguistics, textual analysis, natural language processing, multinomial inverse regression, MNIR, non-answers
JEL Classification: D80, D82, G10, G14, G30
Suggested Citation: Suggested Citation