Sentiment analysis on Twitter data towards climate action
Understanding the progress of the Sustainable Development Goals (SDGs) proposed by the United Nations (UN) is important, but difficult. In particular, policymakers would need to understand the sentiment within the public regarding challenges associated with climate change. With this in mind and the...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123023004140 |
| _version_ | 1797682497800110080 |
|---|---|
| author | Emelie Rosenberg Carlota Tarazona Fermín Mallor Hamidreza Eivazi David Pastor-Escuredo Francesco Fuso-Nerini Ricardo Vinuesa |
| author_facet | Emelie Rosenberg Carlota Tarazona Fermín Mallor Hamidreza Eivazi David Pastor-Escuredo Francesco Fuso-Nerini Ricardo Vinuesa |
| author_sort | Emelie Rosenberg |
| collection | DOAJ |
| description | Understanding the progress of the Sustainable Development Goals (SDGs) proposed by the United Nations (UN) is important, but difficult. In particular, policymakers would need to understand the sentiment within the public regarding challenges associated with climate change. With this in mind and the rise of social media, this work focuses on the task of uncovering the sentiment of Twitter users concerning climate-related issues. This is done by applying modern natural-language-processing (NLP) methods, i.e. VADER, TextBlob, and BERT, to estimate the sentiment of a gathered dataset based on climate-change keywords. A transfer-learning-based model applied to a pre-trained BERT model for embedding and tokenizing with logistic regression for sentiment classification outperformed the rule-based methods VADER and TextBlob; based on our analysis, the proposed approach led to the highest accuracy: 69%. The collected data contained significant noise, especially from the keyword ‘energy’. Consequently, using more specific keywords would improve the results. The use of other methods, like BERTweet, would also increase the accuracy of the model. The overall sentiment in the analyzed data was positive. The distribution of the positive, neutral, and negative sentiments was very similar in the different SDGs. |
| first_indexed | 2024-03-12T00:00:35Z |
| format | Article |
| id | doaj.art-ee44e321b0c74d5e8fa44131b33caee9 |
| institution | Directory Open Access Journal |
| issn | 2590-1230 |
| language | English |
| last_indexed | 2024-03-12T00:00:35Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj.art-ee44e321b0c74d5e8fa44131b33caee92023-09-18T04:30:38ZengElsevierResults in Engineering2590-12302023-09-0119101287Sentiment analysis on Twitter data towards climate actionEmelie Rosenberg0Carlota Tarazona1Fermín Mallor2Hamidreza Eivazi3David Pastor-Escuredo4Francesco Fuso-Nerini5Ricardo Vinuesa6Department of Applied Mathematics, KTH Royal Institute of Technology, Stockholm, SwedenPolytechnic University of Madrid, Madrid, SpainFLOW, Engineering Mechanics, KTH Royal Institute of Technology, Stockholm, SwedenFLOW, Engineering Mechanics, KTH Royal Institute of Technology, Stockholm, SwedenLifeD Lab, Madrid, SpainUnit of Energy Systems Analysis (dESA), KTH Royal Institute of Technology, Stockholm, Sweden; KTH Climate Action Centre, Stockholm, SwedenFLOW, Engineering Mechanics, KTH Royal Institute of Technology, Stockholm, Sweden; KTH Climate Action Centre, Stockholm, Sweden; Corresponding author.Understanding the progress of the Sustainable Development Goals (SDGs) proposed by the United Nations (UN) is important, but difficult. In particular, policymakers would need to understand the sentiment within the public regarding challenges associated with climate change. With this in mind and the rise of social media, this work focuses on the task of uncovering the sentiment of Twitter users concerning climate-related issues. This is done by applying modern natural-language-processing (NLP) methods, i.e. VADER, TextBlob, and BERT, to estimate the sentiment of a gathered dataset based on climate-change keywords. A transfer-learning-based model applied to a pre-trained BERT model for embedding and tokenizing with logistic regression for sentiment classification outperformed the rule-based methods VADER and TextBlob; based on our analysis, the proposed approach led to the highest accuracy: 69%. The collected data contained significant noise, especially from the keyword ‘energy’. Consequently, using more specific keywords would improve the results. The use of other methods, like BERTweet, would also increase the accuracy of the model. The overall sentiment in the analyzed data was positive. The distribution of the positive, neutral, and negative sentiments was very similar in the different SDGs.http://www.sciencedirect.com/science/article/pii/S2590123023004140Sentiment analysisNLPSDGBERTClimate changeTwitter |
| spellingShingle | Emelie Rosenberg Carlota Tarazona Fermín Mallor Hamidreza Eivazi David Pastor-Escuredo Francesco Fuso-Nerini Ricardo Vinuesa Sentiment analysis on Twitter data towards climate action Results in Engineering Sentiment analysis NLP SDG BERT Climate change |
| title | Sentiment analysis on Twitter data towards climate action |
| title_full | Sentiment analysis on Twitter data towards climate action |
| title_fullStr | Sentiment analysis on Twitter data towards climate action |
| title_full_unstemmed | Sentiment analysis on Twitter data towards climate action |
| title_short | Sentiment analysis on Twitter data towards climate action |
| title_sort | sentiment analysis on twitter data towards climate action |
| topic | Sentiment analysis NLP SDG BERT Climate change |
| url | http://www.sciencedirect.com/science/article/pii/S2590123023004140 |
| work_keys_str_mv | AT emelierosenberg sentimentanalysisontwitterdatatowardsclimateaction AT carlotatarazona sentimentanalysisontwitterdatatowardsclimateaction AT ferminmallor sentimentanalysisontwitterdatatowardsclimateaction AT hamidrezaeivazi sentimentanalysisontwitterdatatowardsclimateaction AT davidpastorescuredo sentimentanalysisontwitterdatatowardsclimateaction AT francescofusonerini sentimentanalysisontwitterdatatowardsclimateaction AT ricardovinuesa sentimentanalysisontwitterdatatowardsclimateaction |