Optimizing Positive Workplace Emotions: Prophet-ARIMA-LSTM Solutions for Teachers” Job Satisfaction

Since many nations have a serious scarcity of qualified educators and high rates of teacher turnover, it is to everyone's benefit when teachers love what they do for a career. This is because engaged teachers are more invested in their work, have better health in general, and are less likely to leave. The connection between health and happiness on the job is better understood with the help of this suggestion. A wide variety of operations depend on sequencing, including preprocessing, feature selection, and training models. The steps involved in preprocessing include noise filtering, aggregation, and discretization. When selecting features for positive emotion recognition, it is possible to utilize a collection that contains features that are irrelevant or redundant. Training a Prophet-ARIMA-LSTM model requires careful consideration of which attributes to use. The proposed method outperforms two cutting-edge algorithms, ARIMA and LSTM, in every metric. With a grade of 97.34%, the figures showed a significant improvement.