Using Data Mining Techniques to Analyze the Customers Reaction towards Social Media Advertisements
Ashutosh Bansal1, Saleena B.2, Prakash B3 

1Ashutosh Bansal, II Year MCA, School of Computing Science and Engineering, VIT – Chennai Campus.
2Saleena B, Associate Professor, School of Computing Science and Engineering, VIT – Chennai Campus.
3Prakash B, Assistant Professor, School of Computing Science and Engineering, VIT – Chennai Campus.

Manuscript received on 02 March 2019 | Revised Manuscript received on 08 March 2019 | Manuscript published on 30 July 2019 | PP: 1139-1143 | Volume-8 Issue-2, July 2019 | Retrieval Number: B1700078219/19©BEIESP | DOI: 10.35940/ijrte.B1700.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: As social media is in boom, it is becoming very easier for customers to share their views and comments and express their feelings regarding any products which are present in online social media. . If these data can be analyzed efficiently different suggestions can be provided to the company regarding to improvise their products sale. It becomes easier for the company to understand the customer’s reaction after seeing the advertisements of the products posted on social media. This research focuses on analyzing the sentiments of customers based on the comments and reviews of products available in Facebook. Sentimental Analysis is performed to analyze the customer comments as positive, negative and neutral and later they are labeled as 0 or 1. After the labeling process, a comparative analysis is performed using different classification algorithms. The classification algorithms used are K Nearest Neighbors (KNN), Support Vector Machine (SVM) and Naïve Bayes Classifier. The classification algorithm with the highest accuracy is identified to predict the sales of online products.
Index Terms: Social Media, Classification, Reviews, opinion Mining, Sentiment Analysis, Feedback

Scope of the Article: Classification