International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 04 | Apr -2017
p-ISSN: 2395-0072
www.irjet.net
Sentiment Analysis for Political Reviews using AAVN Combinations Praniti R. Thanvi1, Nikhita S. Sontakke2, Shashwati R. Waghmare3, Zankhana S. Patel4, Prof. Sachin Gavhane5 1Department
of Information Technology, Atharva College of Engineering, Maharashtra, India of Information Technology, Atharva College of Engineering, Maharashtra, India 3Department of Information Technology, Atharva College of Engineering, Maharashtra, India 4Department of Information Technology, Atharva College of Engineering, Maharashtra, India 5 Professor, Department of Information Technology, Atharva College of Engineering, Maharashtra, India ---------------------------------------------------------------------***--------------------------------------------------------------------2Department
Abstract- Sentiment analysis is to separate and group
single thing. So it is very difficult to evaluate reviews manually for a particular thing. People usually misinterpret the reviews and finally come to wrong conclusion. So to deal with this problem an attempt is made to propose software for analyzing the tweets of people on political reviews. To classify whether the expressed opinion in a document, a sentence or an entity feature/aspect is positive or negative or neutral. The proposed paper presents Naive Bayes Algorithm to classify the tweets into Positive, Negative and neutral by assigning the polarity from -1 to +1.
opinions in the composed content. It is one of the major tasks of NLP. Sentiment analysis is a growing field at the intersection of linguistics and computer science that attempts to automatically determine the sentiment contained in text. As many users express their political views on various social networking sites, tweets become valuable sources of people's opinions. This data can be efficiently used to infer people's opinions for marketing or social studies. This paper represents the strategy to classify tweet sentiment using Naive Bayes technique based on three categories; positive, negative or neutral. A method for analyzing the tweets of people on political views by using Adverb-Adjective-Verb-Noun(AAVN) combinations. Separate positive and negative condensed results are created which is useful for the client in choice making.
2 .PREVIOUS WORK Numerous study has been done in determine and classify sentiment of tweets in Twitter. Both supervised and unsupervised techniques are used. Supervised technique such as Naïve Bayes Algorithm[1]. Some other papers have shown an AAVN based sentiment analysis technique deploying linguistic analysis of adverbs, adjective, abstract noun and categorized verb, the paper defines a set of general axioms for opinion analysis to determine a functional value of the sentiment analysis[2]. The paper suggest ,Text mining can be applied to many fields like in the digital newspaper to do politic sentiment analysis. The sentiment analysis is applied to get information from digital news articles about its positive or negative sentiment regarding particular politician. The model used to analyze digital newspaper sentiment polarity using Naïve Bayes classifier method. It uses a set of initial data to begin with which will be updated when new information appears. The study showed promising result where tested and can be implemented to some other sentiment analysis problems[3]. It states that machine learning approach in which machines analyze and classify the human’s sentiments, emotions, opinions etc about some topic which are expressed in the form of either text or speech. The textual data available in the web is increasing day by day[4]. Some paper approach on opinion mining, on the particular blogs or forums[5].
Keywords-Sentiment analysis, linguistic, Naïve Bayes, Adverb-Adjective-Verb-Noun (AAVN).
1 . INTRODUCTION Till date, there has been a rapid of change in web services, internet technology, various types of social media sites such as discussion forums, micro blogs, and peer-to peer networks provides a affluent of information as well as posting online opinions/reviews about particular person or product has tremendously became a popular way for sharing their opinions or thoughts about particular political party/politician or services. The social networking site Twitter will be the targeted social media site for this paper. Nowadays, billions of users are using twitter which can be used as rich source of data for mining information. By using sentiment analysis for political reviews it would be helpful for the study of different political parties or politician and will also be helpful for the users to make a right choice who do not have much or no knowledge about politics. Now problem in sentiment analysis is classifying the polarity of a given text at the document, sentence, or feature/aspect level. People have different opinions for
© 2017, IRJET
|
Impact Factor value: 5.181
|
ISO 9001:2008 Certified Journal
|
Page 72