FOOD REVIEW ANALYSIS USING THE SENTIMENT ANALYSIS AND NEURAL NETWORK

Mrs.B.Deepa1 MS.M.Deepika2 ,S.Mohanlal3,S.Vithyasagar4 ,P.Balamurugan5

 1Project coordinator, Department of Computer Science and Engineering, Nandha Engineering College (Autonomous), Erode, Tamilnadu, India

2Assistant Professor, Department of Computer Science and Engineering, Nandha Engineering College (Autonomous), Erode, Tamilnadu, India

3,4,5 UG Scholar, Department of Computer Science and Engineering, Nandha Engineering College (Autonomous), Erode, Tamilnadu, India

 Email id:deepika.m@nandhaengg.org2 , mohanlal.19cs067@nandhaengg.org3

Abstract. A consumer’s complaints present food or reporting agency with an opportunity to identify and rectify specific problems with their current product or service. The foods that are receiving customer complaints filed against them will analyze the complaint data to provide results on where the most complaints are being filed, what products/ services produce the most useful complaints and other data. This project assists foods in identifying the location and types of errors for resolution, leading to increased customer satisfaction to drive revenue and profitability. This project finds a correlation between complaints, companies and consumers to refine company applications to better accommodate consumer needs using k-means clustering. In addition, using SVM classification, the complaints sentiment values are analyzed and classified into positive or negative reviews. The project is designed using Python. The objectives of this study is: a) To give the estimated sentiment prediction of the subject based on the text reviews/complaints sent by the customers. b) To carry out Sentiment analysis so that the review is judged as either positive or negative. c) To find Percentage of positive/negative reviews. d) To give exact sentiment numerical values for various words and so classification such as positive or negative should be accurate. e) To apply neural network such that it helps to classify the given food review details into one of the predefined reviews.

Keywords: Sentiment Analysis, SVM Classification, Machine Learning, Consumer Reviews.