Enhanced Aspect Sentiment Analysis For Company Profiling And Employee Opinion Mining

Abstract

With the massive amount of companies and organizations flourish today, ranking them and choosing one out of the many become complex and burdensome task. Many metrics are available for ranking  companies, a generalized metric that considers the various aspects that comprise employee opinions of the companies. An aspect-sentiment based embedding for the companies by studying the reviews of the employee is proposed for solving the aforeknown problem. An all-inclusive dataset of company reviews is prepared from the notorious websiteGlassdoor.com. A hybrid ensemble approach to carry out aspect-level sentiment analysis is proposed. A considerable amount of work has been done on movies, music, politics, etc. This papers aims to apply aspect sentiment analysis for company profiling and employee opinion mining. By providing several insights from the collated embeddings, thus helping users gain a better understanding of their options as well as select companies using customized preferences.