1) The document discusses predicting the addictiveness and lifetime of online games using player behavior data and facial electromyography measurements of emotions. 2) An addictiveness index is defined based on the decline rate of the ratio of player presence over time, and facial muscle activity is measured to quantify emotional responses to different games. 3) A model is created relating emotional strength measurements to addictiveness indexes with 94% accuracy, and is validated with 11% average error rate at predicting addictiveness of unseen games. This could help optimize game development and investment decisions.