| CPC G06Q 50/01 (2013.01) [G06N 5/02 (2013.01); H04L 51/52 (2022.05)] | 10 Claims |
|
1. A computer program product, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code executable by at least one processor to perform operations for:
generating, by a brand effect analyzer, training data from a brand profile, one or more social media profiles, one or more future goals, social media data, traditional media data, and entity preferences of an entity;
performing, by the brand effect analyzer, machine learning using the training data to output a model;
receiving, by the brand effect analyzer, a message from the entity for a social media platform;
identifying, by the brand effect analyzer, additional messages related to the message;
determining, by the brand effect analyzer, a reaction sentiment trend for each topic of the additional messages for a period of time;
determining, by the brand effect analyzer, an indication of whether the message contradicts previous messages made by the entity;
predicting, by the brand effect analyzer, using the model, an effect the message has on a personal brand of the entity in future based on future goals of the entity and based on the reaction sentiment trend for each topic by:
comparing, by the brand effect analyzer, the message to previously expressed statements that the entity has made; and
for another entity having similar future goals, determining, by the brand effect analyzer, an effect that one or more other messages of the another entity had, wherein the one or more other messages have a similar type of content as the message;
providing, by the brand effect analyzer, an indication of whether the message is aligned with the future goals based on the predicted effect and based on the indication of whether the message contradicts the previous messages;
in response to the message being aligned with the future goals, posting, by the brand effect analyzer, the message to the social media platform;
in response to the message not being aligned with the future goals,
providing, by the brand effect analyzer, one or more suggestions to modify the message; and
in response to receiving a modified message with at least one of the one or more suggestions,
determining, by the brand effect analyzer, that the modified message is aligned with the future goals based on a new predicted effect; and
posting, by the brand effect analyzer, the modified message to the social media platform;
tuning, by the brand effect analyzer, the model based on heuristics and configuration settings that determine how much each event impacts the model; and
providing, by the brand effect analyzer, suggested changes to the training data based on an effect of the training data on the model.
|