In order to distinguish between conformity effects and individualbias effects, we need to examine cases in which individual people’s opinions do not come from exactly the same (single-peaked, say) distribution; for otherwise, the composite of their individual biases could produce helpfulness ratios that look very much like the results of conformity. One natural place to begin to seek settings in which individual bias and conformity are distinguishable, in the
sense just described, is in cases in which there is at least high variance in the star ratings. Accordingly, Figure 3 separates products by the variance of the star ratings in the reviews for that product in our dataset