Abstract
Sentiment analysis or opinion mining is one of the major tasks of NLP (Natural Language Processing). It captures the user’s opinion, feelings, and belief regarding the respective product especially to determine whether the user’s attitude is positive, negative, or neutral. This analysis greatly helps the companies to make necessary changes in their product which in return can overcome the flaws that the product is facing and targets better customer satisfaction. Existing techniques for the sentiment analysis of online product reviews obtained low accuracy and also took more time for training. To overcome such issues in this paper, a DLMNN is proposed for sentiment analysis of online product review and IANFIS is proposed for future prediction of online product. Here, the sentiment analysis and future predictions are done on the products taken from the food review dataset. First, from the dataset, the data values are partitioned into GB, CB, and CLB scenarios and then the review analysis for each scenario is performed separately using DLMNN and they give the result as positive, negative, and neutral reviews for the product. After the process of review classification based on these three scenarios, the future prediction of the products is done by performing weighting factor and classification using IANFIS. Experimental results are compared with some existing techniques and the results show that the proposed method outperforms other existing algorithms.
Extracting Opinion Targets from Product Reviews using Comprehensive Feature Extraction Model in Opinion Mining
