Emotions Identification by Using Unsupervised Aspect Category Based Sentiment Classification
Vishal Shinde1, Ambika Pawar2, Swati Ahirrao3, Shraddha Phansalkar4
1Vishal Shinde, MTech CS, Symbiosis Institute of Technology, Symbiosis International (Deemed) University, Pune, India.
2Ambika Pawar*, CS & IT ,Symbiosis Institute of Technology, Symbiosis International (Deemed) University, Pune, India.
3Swati Ahirrao, CS & IT ,Symbiosis Institute of Technology, Symbiosis International (Deemed) University, Pune, India.
4Shraddha Phansalkar, CS & IT ,Symbiosis Institute of Technology, Symbiosis International (Deemed) University, Pune, India.
Manuscript received on July 30, 2019. | Revised Manuscript received on August 25, 2019. | Manuscript published on August 30, 2019. | PP: 4224-4230 | Volume-8 Issue-6, August 2019. | Retrieval Number: F8902088619/2019©BEIESP | DOI: 10.35940/ijeat.F8902.088619
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The social media is growing at an astonishing rate; this has resulted in increased online communications. The online communication contains feedbacks, comments, and reviews that are posted on the internet by users. To analyze such data, the paper represents the Aspect-based unsupervised method that applies association rule mining on customer reviews aims to algorithmically identify product aspects, their corresponding opinions from a collection of opinionated reviews. This framework involves four main subtasks: Product aspect identification, Sentiment expression identification, Emotion Detection, Comparison of Products. This paper also represents a Comparative study of sentiment analysis techniques including machine learning technique and lexicon based technique. The comparisons are majorly drawn based on features such as techniques, data source, data scope, and limitations. The proposed framework performs well with F1-Score 76.426%.
Keywords: Aspects, Helpfulness protocol, Machine learning, Sentiment analysis, Spreading activation, Text mining.