Provided is a process that includes: obtaining a training set of n-grams labeled as offensive; causing a machine learning model to be trained based on the training set of n-grams, wherein the machine learning model, when trained, is configured to classify natural language text as offensive or non-offensive; obtaining input natural language text expressing a computer-generated utterance; classifying after causing training, the computer-generated utterance as offensive or non-offensive using the machine learning model; and causing an output to be provided to a recipient, the output being based on whether the machine learning model classifies the computer-generated utterance as offensive or non-offensive.