Text Classification for Feedback Analysis: Automating Rating System with NLP

Abstract - Analysing customer input is essential for improving services, but manual review techniques are laborious and arbitrary. In this paper, an automated text classification grading system based on Natural Language Processing (NLP) approaches is presented. Their efficacy in sentiment categorization is assessed using a variety of machine learning and deep learning models, such as Naïve Bayes, Support Vector Machines (SVM), Recurrent Neural Networks (RNN), and Bidirectional Encoder Representations from Transformers (BERT). Tokenization, stop word removal, and feature extraction using TF-IDF and word embeddings are some of the data preprocessing methods used in the study. The results show that BERT-based models outperform conventional methods and attain the best accuracy. This study demonstrates how NLP may be used to automate feedback analysis, increase productivity, and provide sentiment classification in real time. Future work may focus on expanding the system for multi-lingual feedback and real-time applications.