دانلود رایگان مقاله تحلیلگران سهام در مقابل جمعیت

Abstract

We examine the drivers of crowd wisdom in the financial domain by relating analyst report and social media sentiment via Granger causality (GC) testing based on the wisdom of crowds (WoC) theory. The significance of a large number of the tested time series indicates that analyst reports and social media content are suitable for mutual prediction. We elaborate on the conditions under which crowd cognitive diversity matters, and we derive related measures. The results suggest that the WoC theory can partially explain the GC between the two media types and that both professional analysts and the crowd can outperform one another under favorable circumstances.

6. Conclusion

The aim of this research was to investigate a possible relation between the prediction power of stock analysts’ sentiment and that of “the crowd” (i.e., a large set of social media users). Earlier studies have identified inefficiencies in professional analysts’ decision processes. The WoC theory suggests that the crowd might be able to mitigate these problems. GC testing between the two types of content showed statistically significant relations for a large number of cases in this sample. This finding indicates thatthe two types of content can be used to predict the other in many cases. However, evidence for the similar use of the two types of content is lacking. Similarly, no evidence is provided as to the contents’ complementarity (keeping in mind the emerging issue of multicollinearity). The practical applications of such relationships include algorithmic trading, news reporting, and customer relations. Logit models provide information on the circumstances under which social media content sentiment can be used to predict analyst reports, and vice versa. There is mixed evidence supporting WoC theory. Platform diversity in the social media sample increases the crowd’s success, whereas age diversity decreases it. This finding might be mitigated by a larger sample. A larger sample introduces more variance in company type, spanning a significantly longer period. Evidence for the WoC theory is provided by cases in which social media users arrived at a (collective) opinion, before professional stock analysts were able to include environmental changes into their reports. These results suggest that crowd wisdom can outperform experts if information is instantly available. However, the drivers of crowd wisdom might not be sufficiently explained by the current WoC theory.