Shamathmika, . and Rawat, Sumanu and Hemalatha, S (2017) Categorizing Yelp Reviews - Sentiment Analysis. In: National Workshop-cum-Conference Computer Applications based on Modern Algebra, 01/07/2017, MIT, Manipal.
![]() |
PDF
809.pdf - Published Version Restricted to Registered users only Download (86kB) | Request a copy |
Abstract
Yelp is a service which reveals awareness on local businesses. It allows users from anywhere in the world to rate and review any business. This paper categorizes the textual reviews of businesses provided by yelp for training and testing purposes and assigns a probability for any new review to be of positive or negative sentiment. The reviews on restaurants about food, service, price and ambient are considered for the sentiment analysis. Machine learning algorithms in the NLTK library of python can prove to be very useful in any such project on Natural Language Processing (NLP) and it has been used in this work extensively. The analysis of each algorithm used has been done and they have been compared on the basis of their efficiency (confidence). This paper proposes an implementation of Machine Learning which processes textual statistical data provided by the Yelp dataset as a part of the Yelp Dataset Challenge. The aim is to classify the business reviews into graded categories such that they can be roughly sorted in an order from bad to good or negative to positive
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Uncontrolled Keywords: | Yelp Reviews, Sentiment Analysis, Machine learning |
Subjects: | Engineering > MIT Manipal > Computer Science and Engineering |
Depositing User: | MIT Library |
Date Deposited: | 16 Aug 2017 03:58 |
Last Modified: | 16 Aug 2017 03:58 |
URI: | http://eprints.manipal.edu/id/eprint/149502 |
Actions (login required)
![]() |
View Item |