Abstract
Humor research is supposed to predict whether something is funny. According to its theories and observations, amusement should be predictable based on a wide variety of variables. We test the practical value of humor appreciation research in terms of prediction accuracy. We find that machine learning methods (boosted decision trees) can indeed predict humor appreciation with an accuracy close to its theoretical ceiling. However, individual demographic and psychological variables, while replicating previous statistical findings, offer only negligible gains in accuracy. Successful predictions require previous ratings by the same rater, unless highly specific interactions between rater and joke content can be assessed. We discuss implications for humor research, and offer advice for practitioners designing content recommendations engines or entertainment platforms, as well as other research fields aiming to review their practical usefulness.