Table 7 reports the results of the second-stage model with blog post comments as the dependent variable (N 1⁄4 1,237). The Akaike information criterion for this model was 6,663, the Bayesian information criterion was 6,740, and the likelihood ratio test was significant (w2(13) 1⁄4 100.64, p < .01). Variance inflation factors (VIFs) were all below 1.09, with an average VIF of 1.04, indicating no issues with collinearity. We found a significant main effect of our control variable, average number of followers (b 1⁄4 .3514, p < .01), indicating that this factor significantly drives the number of blog post comments.