Detecting negative experiences in computer-implemented environments

A system comprising:

• a processor;
• and
• a memory in communication with the processor, the memory containing program instructions that, when executed by the processor, are configured to cause the processor to perform a method, the method comprising:
• monitoring frequency data related to a first user metric of a first user during a measurement window, wherein the first user metric is related to the first user's use of a first computer-implemented environment;
• expressing the frequency data related to the first user metric as a first spectrogram;
• inputting the first spectrogram into a convolutional neural network;
• simplifying, by the convolutional neural network, the frequency data related to the first user metric, resulting in a first set of simplified frequency data;
• inputting the first set of simplified frequency data into a predictive neural network;
• determining, by the predictive neural network and based on the first set of simplified frequency data, a likelihood of a negative user experience for the first user;
• and
• altering, based on the likelihood, a parameter of the first user environment.

A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:

• monitor frequency data related to a first user metric of a first user during a first measurement window, wherein the first user metric is related to the first user's use of a first computer-implemented environment;
• express the frequency data related to the first user metric as a first spectrogram;
• input the first spectrogram into a first convolutional neural network;
• simplify, by the first convolutional neural network, the frequency data related to the first user metric, resulting in a first set of simplified frequency data;
• input the first set of simplified frequency data into a predictive neural network;
• determine, by the predictive neural network and based on the first set of simplified frequency data, a likelihood of a negative user experience for the first user;
• and
• alter, by the processor and based on the likelihood, a parameter of the first user environment.