Sentiment Analysis Using Machine Learning of Unemployment Data in India

With the massive increase in social media data and hypes around Natural Language Processing, opinion mining has become one of the most popular ways to analyze people’s views on a specific topic. Using hashtags, one can obtain tweet data in millions and analyze sentiments. This can be done effectively using Python with its NLP modules available. Studying the attitudes and sentiments of Indian citizens towards the current unemployment rate is the primary purpose of this study. In situations where there may be negative sequences due to people’s aggression, analyzing such content to gauge people’s sentiments can be extremely valuable in managing the situation. Natural Language Processing and other Machine Learning classifiers to perform opinion mining of the tweets posted by Indians are used in this research. About 10,928 tweets have been accumulated, on which sentiment analysis has been performed, considering tweets as positive, negative or neutral by classifying them into three categories. ‘Tweepy API’ has been used, along with the hashtags ‘UnemploymentInIndia' and ‘Unemployment’. The data has been cleaned and preprocessed using NLPTK, VADER and other modules provided to us using Python. Study findings suggest that most Indian citizens oppose the unemployment rates in their country, but a minority look to political movements to bring about change.