Social Media as an Alternative to Surveys of Opinions about the Economy

There is interest in using social media content to supplement or even substitute for survey data.  O’Connor et al. (2010) report reasonably high correlations between the sentiment of tweets containing the word “jobs” and survey-based measures of consumer confidence in 2008-2009. Other researchers report a similar relationship through 2011 but after that time it is no longer observed, suggesting such tweets may not be as promising an alternative to survey responses as originally hoped.  But, it’s possible that with the right analytic techniques, the sentiment of “jobs” tweets might still be an acceptable alternative. We explore this possibility by attempting to strengthen the original relationship and then extending the most successful approaches to more recent years. We classify “jobs” tweets into categories whose content is related to employment and categories whose content is not, to see if sentiment of the former correlates more highly with a survey-based measure of consumer sentiment. We use five sentiment-scoring tools, calculate daily sentiment three different ways, and use a measure of association less sensitive to outliers than correlation. None of these approaches improved the size of the relationship in the original or more recent data. We discuss the possibility that weighting and better understanding why users tweet might help recover the original relationship between the sentiment of tweets and survey responses. However, despite the earlier promise of tweets as an alternative to survey responses, we find no evidence that the original relationship was more than a chance occurrence.   Cover 2008-2014 in the United States.