This paper is published in Volume-6, Issue-3, 2020
Area
Computer Science Engineering
Author
Supreeth Basabattini, N. Nikitha, Risita Kumar, Mathiyalagan R.
Org/Univ
Jain University, Bengaluru, Karnataka, India
Pub. Date
25 June, 2020
Paper ID
V6I3-1611
Publisher
Keywords
Machine Learning, Amazon Web Services, Twitter, Sentiment Analysis, Serverless Computing

Citationsacebook

IEEE
Supreeth Basabattini, N. Nikitha, Risita Kumar, Mathiyalagan R.. Optimized social media customer support using machine learning with AWS, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Supreeth Basabattini, N. Nikitha, Risita Kumar, Mathiyalagan R. (2020). Optimized social media customer support using machine learning with AWS. International Journal of Advance Research, Ideas and Innovations in Technology, 6(3) www.IJARIIT.com.

MLA
Supreeth Basabattini, N. Nikitha, Risita Kumar, Mathiyalagan R.. "Optimized social media customer support using machine learning with AWS." International Journal of Advance Research, Ideas and Innovations in Technology 6.3 (2020). www.IJARIIT.com.

Abstract

The rising popularity of social media communication can be witnessed everywhere. Not only individuals but companies too have noticed the importance of communication via social media and persist. Associations between customers and companies can be seen via social media. Customers might choose to publicize their opinions about a service or product via social media. Twitter is exceptionally used for is such cases. In this paper, we will exhibit how everyday customers are publicizing their items or taking the criticism for their items utilizing Web-based social networking systems like Twitter. In this procedure, the framework will consumer messages (tweets) and apply machine learning techniques (SVM, Porter stemming) to analyze the nature of the tweet via sentiment analysis. The results will be shown as tweets regarding positive, negative. We likewise will provide an automated response to the tweet (if found negative) and forward the message contents to the customer care email client for quick analysis and explicit response.