Abstract

The sentiment data provides vital information about the feedback of the user’s opinion, attitude and emotions. The business of product development and digital marketing teams entirely depends upon the outcome of these sentiments and they apply various Data Mining techniques, Machine Learning and Deep Learning approaches to analyse the depth of the dataset. The Sentiment Analysis provides the automatic data mining of reviews, comments, opinions and suggestions, received from various input methods, including text, audio notes, images and emoticons, through Natural Language Processing. The analysis assists in the classification of reviewer feedback in terms of positive, negative and neutral categories. In this study, the opinions shared by individuals over various social networking sites in the case of any big event, the release of any new product or show and political events were analysed. Machine Learning and Deep Learning techniques are discussed and used dominantly to illustrate the outcome of opinions and events. The accurate analysis of vast information shared by individuals free of cost and without any influence can provide vital information for organisations and management authorities. This review analyses various techniques in the field of Aspect-Based Sentiment Analysis along with their features and research scopes and thus, it helps researchers to focus on more precise works in the future. Among the machine learning algorithms, Random Forest performed much better as compared to other methods, and among the Deep Learning approaches, Multichannel CNN outperformed with the highest accuracy of 96.23%. The paper includes the comparative study of multiple Machine Learning and Deep Learning techniques for the evaluation of sentiment data and concludes with the challenges and scope of Sentiment Analysis.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.