International Journal of Computer Engineering and Technology (IJCET)

Source ID:00000005
Volume 9, Issue 2,March - April 2018, Pages 150-161, Page Count - 12

CNSM: COSINE AND N-GRAM SIMILARITY MEASURE TO EXTRACT REASONS FOR SENTIMENT VARIATION ON TWITTER

Savitha Mathapati (1) Anil D (2) Tanuja R (3) S H Manjula (4) Venugopal K R (5)

(1) Department of Computer Science and Engineering, University Visvesvaraya College of Engineering (UVCE), Bengaluru, Karnataka, India.
(2) Department of Computer Science and Engineering, University Visvesvaraya College of Engineering (UVCE), Bengaluru, Karnataka, India.
(3) Department of Computer Science and Engineering, University Visvesvaraya College of Engineering (UVCE), Bengaluru, Karnataka, India.
(4) Department of Computer Science and Engineering, University Visvesvaraya College of Engineering (UVCE), Bengaluru, Karnataka, India.
(5) Department of Computer Science and Engineering, University Visvesvaraya College of Engineering (UVCE), Bengaluru, Karnataka, India.

Manuscript ID:- 00000-03141
Access Type : Open Access
Read Full Article


Cite this article:Savitha Mathapati,Anil D,Tanuja R,S H Manjula,Venugopal K R,  Cnsm: Cosine And N-gram Similarity Measure To Extract Reasons For Sentiment Variation On Twitter, International Journal of Computer Engineering and Technology(IJCET), 2018, 9(2), PP.150-161

Manuscript Level Metrics (MLM)

Views Downloads Citations Cited References Social Shares
37 19 1 0

Abstract

An advanced domain has evolved in the field of research over the past decade, called Sentiment Analysis on Social Media. Twitter has made huge impact with more than 500 million Tweets each day. People share their opinion in the form of Tweets on many topics. In this paper, we employ Foreground and Background LDA (FB-LDA) and Reason Candidate and Background LDA (RCB-LDA) model to extract the reasons for sentiment variation. Emerging topics or Foreground topics within the sentiment variation period are highly related to the reasons for sentiment variation, whereas Background topics are discussed from long time and do not add to the sentiment variation. FB-LDA model filter out Background topics from the Foreground tweet set and extract the required Foreground topics that contribute for the reason for sentiment variation. RCB-LDA model finds more relevant tweets of the Foreground topic that are extracted in FB-LDA model and rank them to get Reason Candidates. To extract Reason more precisely from Reason Candidates, in this paper we propose n-gram similarity matching and Cosine similarity using Latent Semantic Analysis methods. These two methods mine specific reason for sentiment variation.
Author Keywords
LDA Topic Modeling Opinion Mining Public Sentiment Variation Semantic Similarity Tweets
Index Keywords
World Wide Web election polls Comments


ISSN Print: 0976-6367 ISSN Online: 0976-6375
Source Type: Journals Document Type: Journal Article
Publication Language: English DOI: 10.34218/IJCET.9.2.2018.016
Abbreviated Journal Title: IJCET Access Type: Open Access
Publisher Name: IAEME Publication Resource Licence: CC BY-NC
Major Subject:Physical Sciences Subject Area classification: Engineering and Technology
Subject area: Media Technology Source: SCOPEDATABASE