Paper Title
Ensemble Models and Summary Score for Hindi ABSA

Abstract
The Aspect Based Sentiment Analysis (ABSA) is a kind of Sentiment Analysis which allows us to associate sentiments to primary features (Aspect Category) of the object or entity. ABSA allows us to determine multiple sentiments, one for each aspect category referenced in the review sentence. In this paper, we propose Ensemble Model for Category-based polarity determination using different set of novel features. We derive Sentence Vector and sentiment features for a review sentence. We propose algorithms for n-gram features (N-Gram) and Category Association Word features (CAW) before building the model. We contribute by deriving extended Hindi ABSA Category dataset and compare the results using our models. We also contribute by deriving the summary score compuation algorithm for each aspect category. The results show that the accuracy of this subtask ranges from 50% to 76% among four major domains. Keywords - Aspect based sentiment analysis, Sentiment classification, Sentence vector, Association word features, Ensemble model, Summary of ABSA.