Start Date

12-17-2013

Description

A wide body of research uses data from social media websites to predict offline economic outcomes such as sales. However, in practice, such data are costly to collect and process. Additionally, sales forecasts based on social media data may be hampered by people’s tendency to restrict the topics they publicly discuss. Recently, a new source of predictive information—search engine logs—has become available. Interestingly, the relationship between these two important data sources has not been studied. Specifically, do they contain complementary information? Or does the information conveyed by one source render the information conveyed by the other source redundant? This study uses Google’s comprehensive index of internet discussion forums, in addition to Google search trend data. Predictive models based on search trend data are shown to outperform and complement forum-data-based models. Furthermore, the two sources display substantially different patterns of predictive capacity over time.

Share

COinS
 
Dec 17th, 12:00 AM

Do Customers Speak Their Minds? Using Forums and Search for Predicting Sales

A wide body of research uses data from social media websites to predict offline economic outcomes such as sales. However, in practice, such data are costly to collect and process. Additionally, sales forecasts based on social media data may be hampered by people’s tendency to restrict the topics they publicly discuss. Recently, a new source of predictive information—search engine logs—has become available. Interestingly, the relationship between these two important data sources has not been studied. Specifically, do they contain complementary information? Or does the information conveyed by one source render the information conveyed by the other source redundant? This study uses Google’s comprehensive index of internet discussion forums, in addition to Google search trend data. Predictive models based on search trend data are shown to outperform and complement forum-data-based models. Furthermore, the two sources display substantially different patterns of predictive capacity over time.