摘要：Nowadays sentiment analysis has become very important, mostly used for huge datasets and helpful for researchers for applying methods and techniques. Amazon’s food data is growing exponentially and traditional systems are unable to process it, so we used Big Data to overcome this problem. In this paper, we explore different methods and techniques of sentiment analysis using apache spark data processing system for big datasets of Amazon Fine Food reviews. Three mechanisms are applied that have more than 80% accuracy named as Linear SVC, Logistic Regression, and Naïve Bayes by using MLlib which is Apache Spark’s library for ML. When applied these methods we realize that Linear SVC performs efficiently than NB and logistic regression..
