Satisfaction Surveys or Online Sentiment: Which Best Predicts Firm Performance?
(A2022-107257)

AUTHORS

Evert de Haan, University of Groningen

ABSTRACT

Survey-based customer satisfaction has been established as a good predictor of future firm performance. These days, customer opinions can also be tracked by electronic word of mouth (eWOM). In this study, I investigate how traditional customer satisfaction performs compared with eWOM sentiment in predicting future firm performance, given each data source’s strengths and weaknesses. To do so, I collect customer satisfaction data from the ACSI, eWOM sentiment data from more than 8.4 million tweets, and 13 financial performance indicators from 46 firms over an eight-year span. I show that negative eWOM is overall the best predictor of future firm performance and that combining predictors is better than just using one predictor. For practitioners it is thus recommended to track both data types to monitor performance. For academics, online sentiment can also be used as an easy-to-collect data source to measure marketing’s impact.