|
INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016 open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15 |
Imp Links for Author
Imp Links for Reviewer
Research Area
Subscribe IJSDR
Visitor Counter
Copyright Infringement Claims
Indexing Partner
|
Published Paper Details
|
|
| Paper Title: | EFFICIENT NATURAL LANGUAGE PROCESSING USED FOR TWITTER DATA BASED ON SENTIMENT ANALYSIS |
| Authors Name: | Prabakaran Natarajan |
| Unique Id: | IJSDR1906066 |
| Published In: | Volume 4 Issue 6, June-2019 |
| Abstract: | Social Media (SM) is a popular source for information retrieval. It is being used for sharing day-to-day events of our lives and the incidents occurring world-wide Twitter, in which users post instantaneous reactions to as well as opinions concerning "everything". People opinions are analyzed based on the Sentiment Analysis (SA). Most commonly Natural Language Processing (NLP) is utilized for SA. Existing works have low accuracy in sentiment classification. To trounce the difficulty, this paper proposed efficient NLP used for SA on the twitter data. Proposed system has five phases. Originally, the input data is taken from the ruby API twitter data set. Thus, the data is preprocessed utilizing Stop Word Removal (SWR), stemming, tokenization, and removal of numbers. Secondly, emoticons, non-emoticons, and lexicon features are extorted. Thirdly, the extorted features are ranked using SentiWordNet dictionary. In the fourth stage, the ranked features are classified using Modified Artificial Neural Network (MANN); the modification is done utilizing Cuckoo search (CS) algorithm. The CS algorithm is utilized for optimizing the weight for each neuron layer. Finally, the system is tested utilizing K-Fold Cross-Validation. Experimental results contrasted with the previous Modified Decision Tree (MDT) technique in respects of accuracy, recall along with F-measure, precision, average sentiment score and computation time. The proposed twitter data SA indicates better when compared with existing methods. |
| Keywords: | Big data, Natural Language Processing (NLP), Sentiment Analysis, Modified Artificial Neural Network (MANN), Cuckoo search (CS), Modified Decision Tree (MDT) |
| Cite Article: | "EFFICIENT NATURAL LANGUAGE PROCESSING USED FOR TWITTER DATA BASED ON SENTIMENT ANALYSIS", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.4, Issue 6, page no.368 - 380, June-2019, Available :http://www.ijsdr.org/papers/IJSDR1906066.pdf |
| Downloads: | 000337073 |
| Publication Details: | Published Paper ID: IJSDR1906066 Registration ID:190745 Published In: Volume 4 Issue 6, June-2019 DOI (Digital Object Identifier): Page No: 368 - 380 Publisher: IJSDR | www.ijsdr.org ISSN Number: 2455-2631 |
|
Click Here to Download This Article |
|
| Article Preview | |
|
|
|
Major Indexing from www.ijsdr.org
| Google Scholar | ResearcherID Thomson Reuters | Mendeley : reference manager | Academia.edu |
| arXiv.org : cornell university library | Research Gate | CiteSeerX | DOAJ : Directory of Open Access Journals |
| DRJI | Index Copernicus International | Scribd | DocStoc |
Track Paper
Important Links
Conference Proposal
ISSN
 |
 |
DOI (A digital object identifier)
  Providing A digital object identifier by DOI How to GET DOI and Hard Copy Related |
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
 |
 |
 |
Social Media
Indexing Partner |
|||
| Copyright © 2024 - All Rights Reserved - IJSDR | |||
Facebook Twitter Instagram LinkedIn