The Rise of Search Terms to Predict Stock Price Movements

The volume of search for a particular company and its website through the Internet and search engines can be a metric on its web popularity. In this paper we study the relation, if any, between the volume of users' search for a company's information and company's stock price change. Our tests were on companies from the S&P 500 and the keywords information were extracted using Google Trends tool. Results from the study show that some keywords are correlated positively with companies. The more those keywords are searched reflects an increase on the stock price which agrees with the attention theory provided in the literature. On the other hand, results show that the increase of search of other keywords correlates negatively with other companies' stock prices. This also agrees with the results from other stream of research that recommends the use of sentiment analysis to contextualize the search.This result has implications for both researcher and practitioners. From a research perspective, the paper re-evaluated previous results in the literature. It also identifies the issues in the dataset used by previous research and provides a new dataset whose accuracy is tested and that solves the is-sues identified. From practitioner's perspective, the paper provides a dataset that can be used as input for individual investors for their investment decisions