Sentiment Analysis on Educational Tweets: A Case of National Education Policy 2020

Due to COVID-19 pandemic lockdowns, the transition from traditional class-room-based approaches, there has been rise in online education. There is a growing need to adopt the best global academic and innovative practices and implement the National Education Policy-2020 (NEP) in Indian education. This study uses a dataset, NEP_Eduset, created by gathering tweets about education. An attempt has been made in this study to examine the tweets by preprocessing, generating labels or sentiments using standard tools and libraries in Python language, applying and comparing various machine learning (ML) algorithms. ML approaches are powerful and used in various applications ranging from sentiment analysis, text analysis, natural language processing (NLP), image processing, object detection. ML methods are widely used in sentiment analysis tasks and text annotations. This work uses Text-Blob, Valence Aware Dictionary for Sentiment Reasoning (VADER), and a Customized method, Senti_NEP to analyze the sentiment score of tweets’ text. Senti_NEP method is shown is produce better results for various experiments conducted for the dataset, NEP_Eduset. Various supervised ML models have been applied for text classification of user sentiment. Word2Vec feature extraction technique has been applied to build and evaluate the models. Performance metrics such as precision, accuracy, F1 score and recall have been used to evaluate the ML models. The results reveal that the support vector machine and random forest classifiers achieve higher accuracy with Word2Vec. The performance results have been compared with VADER, TextBlob and Senti_NEP. It has been found that the Senti_NEP method produces better results.