Analyzing adverbs impact for sentiment analysis using hadoop

The research focuses on the impact of different types of adverbs and their all possible combinations that are used for sentiment classification using Hadoop to improve efficiency and scalability. We have analyzed the impact of Adverb forms, i.e., Adverb, General Adverbs, General Comparative Adverbs, Adverbs of time, Degree Adverbs, Degree Comparative Adverbs, Preposition Adverb, and Locative Adverbs for sentiment analysis. The experiments are performed using an annotated dataset of 58,258 office product reviews collected from Amazon. The findings of this work shows that General Comparative Adverbs and General Adverbs are important polarity bearing words for neutral opinions, similarly Locative Adverbs and Preposition Adverbs bear significant information for positive and negative opinions respectively.