Hash Tag-Based Sentiment Analysis Using A Deep Learning Approach

Social commerce uses a variety of social networking sites like Facebook, Instagram, Twitter, Pinterest, and business Whatsapp as a platform to promote products and services. Since advertising, a product, or service in s-comm will reach as high as a possible number of users on networking sites. Ads will spread virally by sharing among friends and friends of friends. So that wider reachability is possible and shortly will get the customer for our business. The success of an s-comm campaign is measured by the degree to which consumers interact with the sellers through review comments, likes, and shares between friends. Customer behavior analysis is needed for s-comm marketing because social commerce can significantly boost economic growth. The sentiment analysis of customer recommendations was investigated using a dataset of women's s-comm apparel hashtags and reviews. So for such reviews are experimented with different machine learning algorithms (Decision tree, SVM, Random Forest, KNN, Naïve Bayes and LSTM). These models handled the common English reviews and compared the metrics (Accuracy, Sensitivity and Specificity) with one another. Instead of working with individual model, this paper introduces a novel hybrid approach that integrates CNN and Ada Boost LSTM algorithms to provide better results in sentiment analysis when compared to other machine learning algorithms mentioned above. While considering the hash tag with common review comments the hybrid system is out performed. The comparison analysis is done for performance matrices namely accuracy of 98%, specificity of 98.1%, and sensitivity of 98.1%. In the s-commerce transaction industry, this hybrid approach will help to create a deeper understanding of consumer sentiment analysis and psychologically attract clients.