THE STUDY OF INCREMENTAL PROCEDURE WITH DEEP LSTM FOR MULTICLASS SENTIMENT ANALYSIS CONTEXT WITH ON EDUCATIONAL DATA

In Sentiment Analysis, Machine Learning (ML) and Deep Learning (DL) algorithms used to understand people’s nature and responses to events. Sentiment analysis widely used across various fields to study opinions or feedback and to improve services. It used to analyzed sentiment documents and classify their polarity as positive, negative, or neutral. Recent research work and studied that are ongoing are focused on Multiclass Sentiment Analysis (MCSA) aimed at analyzed textual documents and derived insights from them. A study used LSTM neural networks had presented a comprehensive analysis of Students academic performance measurement data that transformed measurement metrics into three sentiment categories. The educational systems involved in learning, decision-making, and evaluation process improved through the Students performance of Multiclass Sentiment Analysis. A study used Long Short-Term Memory (LSTM) neural networks for measured student’s performance data achieved excellent performance with an accuracy of 99.89% through careful feature engineering, class balancing, and LSTM architecture optimization. The proposed research provided insights into the applications of these technologies across various fields of machine learning and deep learning including education, customer voice, workforce analysis, politics, digital marketing, and social media monitoring, and established a framework for this.