• RAMSHANKAR N

      Articles written in Sadhana

    • A novel recommendation system enabled by adaptive fuzzy aided sentiment classification for E-commerce sector using black hole-based grey wolf optimization

      RAMSHANKAR N JOE PRATHAP P M

      More Details Abstract Fulltext PDF

      Sentiment analysis is the most frequently adopted technique and is also termed as opinion mining. A numerous data is generated by the E-Commerce portals. These data will assist the online retailers for knowing the expectation of customers. From the numerous sources, sentiment analysis can process huge amount of onlineopinions. This paper develops a novel sentiment classification approach, named BH-GWO-Fuzzy, in E-commerce application for framing an efficient recommendation system. The proposed model undergoes five processingsteps, such as (a) Data acquisition, (b) Pre-processing, (c) Feature extraction, (d) Weighted feature extraction, and (e) Classification. The pre-processing is done by three steps, namely stop word removal, stemming, and blank space removal. Further, the feature extraction is performed by measuring the joint similarityscore and cross similarity score for the positive, negative and neutral keywords from the tweets. From the resultant features, the weighted feature extraction is carried out, in which the weight is multiplied with the features to attain the better scalable feature suitable for classification. Here, the weight is tuned or optimized by the hybrid Black Hole-based Grey Wolf Optimization (BH-GWO). The BH-GWO is developed by integrating BH and GWO algorithms. After that, the extracted features are subjected to Adaptive Fuzzy Classifier, in which the membership function is optimized by the same hybrid BH-GWO algorithm. Finally, the sentiment classification for recommendation system will be empirically evaluated against the gathered benchmark dataset using diverse machine learning algorithms.The accuracy of the BH-GWO-Fuzzy is 11.7% better than Fuzzy, 28.3% better than K-Nearest Neighbor (KNN), 20.2% better than Support Vector Machine (SVM), and 18.75% better than Neural Network (NN) at learning percentage 45 for dataset 1.

  • Sadhana | News

    • Editorial Note on Continuous Article Publication

      Posted on July 25, 2019

      Click here for Editorial Note on CAP Mode

© 2021-2022 Indian Academy of Sciences, Bengaluru.