Data processing methods for predictions of media content performance

A computer-implemented method of predicting performance data for a piece of media content that is consumable by a plurality of users, each of the plurality of users being at a respective client device, the method comprising:

• collecting, at each of a plurality of the respective client devices, raw input data indicative of a user response to the piece of media content during consumption of the piece of media content;
• processing the collected raw input data to:
• extract a time series of descriptor data points for each user response;
• obtain a time series of emotional state data points for each user response;
• determine a predictive parameter from the time series of descriptor data points or the time series of emotional state data points for each of the plurality of users by:
• calculating a temporal difference between the extracted time series of the descriptor data points or the time series of emotional state data points;
• normalizing the temporal difference to produce a normalized temporal difference by subtracting an average difference from the temporal difference;
• segmenting the time series into a plurality of time bins having a predetermined duration;
• calculating a maximum of the normalized differences;
• weighting and summing the values of each of the plurality of time bins;
• and
• normalizing by the length of the piece of media content;
• and
• obtain a plurality of group predictive parameters based on the predictive parameters determined for the plurality of users by generating a descriptive statistic indicative of the predictive parameter across the plurality of users;
• inputting the plurality of group predictive parameters to a classification model which operates to map the obtained plurality of group predictive parameters of the time series of descriptor data points or the time series of emotional state data points to predict performance data for the piece of media content;
• predicting performance data by operating the classification model;
• and
• outputting the predicted performance data for the piece of media content obtained from the classification model,
• wherein the predictive parameter is a normalized quantitative indicator of relative change in the response of the user to the piece of media content, and wherein each group predictive parameter is a descriptive statistic indicative of the respective predictive parameter across the plurality of users.