You Are What You Search : Can Google Search Queries Accurately Measure Investor Sentiment?

Abstract: This paper aims at investigating the relationship between volumes of Google searches for finance related words and stock market movements in Sweden. The method follows Preis et al. (2013) who show that a superior investment strategy can be developed by incorporating search volumes data in the decision making process. Moreover, several econometric regression models will be applied in order to evaluate the significance of Google search volumes as a proxy for investor sentiment. The findings suggest that Google search volume data can predict short term downturns for certain words relating to finance which also bear a negative connotation. For some other words which are strongly related to household savings, the Google strategy can predict upturns in the market. However, any excess returns from the Google investment strategy are diminished to zero when transaction costs are incorporated into the model. This research could save policy makers time and resources by measuring investor sentiment for a fraction of the cost of current methods.