AccScience Publishing / AJWEP / Volume 16 / Issue 2 / DOI: 10.3233/AJW190013
RESEARCH ARTICLE

Renewable Energy Sources for Clean Environment: Opinion Mining

Achin Jain1 Vanita Jain2*
Show Less
1 University School of Information, Communication & Technology, GGSIPU
2 Bharati Vidyapeeth’s College of Engineering, Bharati Vidyapeeth’s College of Engineering
AJWEP 2019, 16(2), 9–14; https://doi.org/10.3233/AJW190013
Submitted: 25 January 2019 | Revised: 1 March 2019 | Accepted: 1 March 2019 | Published: 24 April 2019
© 2019 by the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

 

Use of conventional energy sources causes enormous amount of pollution leading to the problem  of global warming. Most of the countries in Asia are facing the problem of pollution leading to lots of health  problems. To curb these problems, renewable energy sources play a very important role. Sentiment analysis is  used to analyze opinions of the user for decision making with the help of natural language processing techniques.  Opinions are the sentiment or emotions about a subject that is expressed by a user. To study about the emotions of  people about alternate energy sources we have carried out comparative sentiment analysis on various renewable  energy sources using Twitter data. In our paper we have considered five sources namely: Solar energy, Bioenergy,  Wind power, Hydro power and Geothermal energy. Data has been collected from Twitter which is approximately  20,000 tweets for each energy source amounting approximately to 100,000 data which have been considered for  analysis. Eight sentiments are calculated for each renewable energy source. It has been found that the people’s  opinion about renewable energy sources—mainly solar and wind energy—fetches most tweets and people are  more positive towards renewable energy sources for better environment.

Keywords
Sentiment analysis
Twitter
renewable energy sources
social mining
Conflict of interest
The authors declare they have no competing interests.
References

Crannell, W.C., Clark, E., Jones, C., James, T.A. and J.  Moore (2016). A pattern-matched Twitter analysis of US  cancer-patient sentiments. Journal of Surgical Research,  206(2): 536-542.

Injadat, M., Salo, F. and A.B. Nassif (2016). Data mining  techniques in social media: A survey. Neurocomputing,  214: 654-670.

Kunz, N.C., Kastelle, T. and C.J. Moran (2017). Social  network analysis reveals that communication gaps mayprevent effective water management in the mining sector.  Journal of Cleaner Production, 148: 915-922.

Manek, A.S., Shenoy, P.D., Mohan, M.C. and K.R. Venugopal  (2017). Aspect term extraction for sentiment analysis in  large movie reviews using Gini Index feature selection  method and SVM classifier. World wide web, 20(2): 135-154.

Medhat, W., Hassan, A. and H. Korashy (2014). Sentiment  analysis algorithms and applications: A survey. Ain Shams  Engineering Journal, 5(4): 1093-1113.

Óskarsdóttir, M., Bravo, C., Verbeke, W., Sarraute, C.,  Baesens, B. and J. Vanthienen (2016). A comparative  study of social network classifiers for predicting churn in  the telecommunication industry. IEEE/ACM International  Conference on Advances in Social Networks Analysis and  Mining (ASONAM), 2016: 1151-1158.

  Pang, B. and L. Lee (2008). Opinion mining and sentiment  analysis. Foundations and Trends® in Information  Retrieval, 2(1–2): 1-135.

Pill, S., Harvey, S. and B. Hyndman (2017). Novel research  approaches to gauge global teacher familiarity with gamebased teaching in physical education: An exploratory#  Twitter analysis. Asia-Pacific Journal of Health, Sport and Physical Education, 8(2): 161-178.

Renewable Energy Statistics – Accessed from http:// ec.europa.eu/eurostat/statistics-explained/index.php/ Renewable_energy_statistics

Taboada, M., Brooke, J., Tofiloski, M., Voll, K. and M. Stede  (2011). Lexicon-based methods for sentiment analysis.  Computational Linguistics, 37(2): 267-307.

Tang, J., Chang, Y., Aggarwal, C. and H. Liu (2016). A  survey of signed network mining in social media. ACM  Computing Surveys (CSUR), 49(3): 42.

Tayal, D.K. and S.K. Yadav (2017). Sentiment analysis on  social campaign “Swachh Bharat Abhiyan” using unigram  method. AI & Society, 32(4): 633-645.

Share
Back to top
Asian Journal of Water, Environment and Pollution, Electronic ISSN: 1875-8568 Print ISSN: 0972-9860, Published by AccScience Publishing