Training and using a sentiment machine learning module to receive as input haptic metric values to determine a sentiment score for text to provide to an interactive program

Abstract

Provided are a computer program product, system, and method for training and using a sentiment machine learning module to determine a sentiment score. Haptic metric values are collected from haptic interfaces embedded in input devices users control to generate content. A training set associates a haptic metric value resulting from a user interacting with an input device to generate content and a sentiment score for the content. A sentiment machine learning module is trained to output the sentiment score in a training set from input comprising the haptic metric value. A haptic metric value received from an input device, used by an active user interacting with the interactive program, is inputted to the sentiment machine learning module to output a haptic sentiment score for the haptic metric value. The haptic sentiment score is provided to an interactive program to control the interactive program communications with the active user.