Gradient Boosting Approach for Sentiment Analysis for Job Recommendation and Candidate Profiling

Abstract

Sentiment Analysis has increasingly been used nowadays in many applications to evaluate opinion of public about products, policies, movies, politics. It is also used by government and law enforcement to understand behavior of people. One of the potential applications of sentiment analysis is candidate profiling and job recommendation. In the proposed research work, we evaluated the performance of supervised machine learning algorithms on dataset generated by us from twitter and indeed. We illustrated the steps involved in preproccesing the dataset generated through web scraping and making it ready for feeding into supervised algorithms. From our experimental study it is observed that Gradient Boosting Classifier gave the highest classification accuracy of 78.08 percent and AUC score of 0.819 on the test dataset.