“…[33] F54 verified purchase [19] Amazon.com 2014 [2], [4], [5], [19], [32], JD.com [3], TripAdvisor [33], Ciao.co.uk [34], Drugs.com, Yelpf.com [5] 10-fold CV [3], Time-based [19], Total sampling [19], Simple random [19] M2 [4], M4 [5], [32], M8 [2], M9 [3], M11 [33], M11 logistic regression in XGB classifier [19] and CNN/cross entropy loss [19], [34] M12 Zero Inflated Poisson [31] This study helpful vote (R3 ) review text (F4 ) Amazon.com 2018 [22] and IMDb [23] Adjusted 10fold CV (ACV), adaptive window size (AWS) Distribution-adapted model in LM, XGB and CNN Researchers were motivated by the results in the helpfulness rating to continue to employ both models to estimate the number of helpful votes [4], [6], [7], [32] although the distribution is not normal. The central limit theory also supports this condition that a large dataset tends toward a normal distribution in many situations, even if the original variables themselves are not normally distributed [38].…”