Modeling expectation mismatches

A non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors, cause the processors to determine mismatches in evaluations, the determining mismatches comprising:

• receiving a first evaluation of an employee from a supervisor of the employee, the first evaluation comprising one or more supervisor comment ratings and one or more supervisor numerical ratings, each of the supervisor comment ratings and supervisor numerical ratings corresponding to an evaluation category;
• receiving a second evaluation of the employee from the employee, the second evaluation comprising one or employee comment ratings and one or more employee numerical ratings, each of the employee comment ratings and employee numerical ratings corresponding to the evaluation category;
• determining one or more first sentiment polarity scores of the supervisor comment ratings and one or more second sentiment polarity scores of the employee comment ratings comprising training a neural network and using the trained neural network to determine if the comment ratings are positive or negative and assigning a corresponding polarity value;
• determining one or more polarity mismatch scores based on the first sentiment polarity scores and the second sentiment polarity scores;
• determining one or more average differential ratings based on the supervisor numerical ratings and the employee numerical ratings;
• and
• combining the polarity mismatch scores and the average differential ratings to generate a final expectations mismatch score for the employee;
• the neural network training comprising forming probability-weighted associations between input and results, adjusting weighted associations and repeating the forming probability-weighted associations between inputs and results until a criteria is reached;
• and
• generating the final expectations mismatch score as a specialized data structure.

A human capital management system comprising:

• one or more processors programmed to determine mismatches in evaluations, the determining mismatches comprising:
• receiving a first evaluation of an employee from a supervisor of the employee, the first evaluation comprising one or more supervisor comment ratings and one or more supervisor numerical ratings, each of the supervisor comment ratings and supervisor numerical ratings corresponding to an evaluation category;
• receiving a second evaluation of the employee from the employee, the second evaluation comprising one or employee comment ratings and one or more employee numerical ratings, each of the employee comment ratings and employee numerical ratings corresponding to the evaluation category;
• determining one or more first sentiment polarity scores of the supervisor comment ratings and one or more second sentiment polarity scores of the employee comment ratings comprising training a neural network and using the trained neural network to determine if the comment ratings are positive or negative and assigning a corresponding polarity value;
• determining one or more polarity mismatch scores based on the first sentiment polarity scores and the second sentiment polarity scores;
• determining one or more average differential ratings based on the supervisor numerical ratings and the employee numerical ratings;
• and
• combining the polarity mismatch scores and the average differential ratings to generate a final expectations mismatch score for the employee;
• the neural network training comprising forming probability-weighted associations between input and results, adjusting weighted associations and repeating the forming probability-weighted associations between inputs and results until a criteria is reached;
• and
• generating the final expectations mismatch score as a specialized data structure.