Climate Change Sentiment Analysis Using Lexicon, Machine Learning and Hybrid Approaches

Abstract

The emissions of greenhouse gases, such as carbon dioxide, into the biosphere have the consequence of warming up the planet, hence the existence of climate change. Sentiment analysis has been a popular subject and there has been a plethora of research conducted in this area in recent decades, typically on social media platforms such as Twitter, due to the proliferation of data generated today during discussions on climate change. However, there is not much research on the performances of different sentiment analysis approaches using lexicon, machine learning and hybrid methods, particularly within this domain-specific sentiment. This study aims to find the most effective sentiment analysis approach for climate change tweets and related domains by performing a comparative evaluation of various sentiment analysis approaches. In this context, seven lexicon-based approaches were used, namely SentiWordNet, TextBlob, VADER, SentiStrength, Hu and Liu, MPQA, and WKWSCI. Meanwhile, three machine learning classifiers were used, namely Support Vector Machine, Naïve Bayes, and Logistic Regression, by using two feature extraction techniques, which were Bag-of-Words and TF–IDF. Next, the hybridization between lexicon-based and machine learning-based approaches was performed. The results indicate that the hybrid method outperformed the other two approaches, with hybrid TextBlob and Logistic Regression achieving an F1-score of 75.3%; thus, this has been chosen as the most effective approach. This study also found that lemmatization improved the accuracy of machine learning and hybrid approaches by 1.6%. Meanwhile, the TF–IDF feature extraction technique was slightly better than BoW by increasing the accuracy of the Logistic Regression classifier by 0.6%. However, TF–IDF and BoW had an identical effect on SVM and NB. Future works will include investigating the suitability of deep learning approaches toward this domain-specific sentiment on social media platforms.

Implementation of Ensemble Machine Learning Classifier and Synthetic Minority Oversampling Technique for Sentiment Analysis of Sustainable Development Goals in Indonesia

“…SDGs 1 [14], [15]; SDGs 2 [16], [17]; SDGs 3 [4], [18], [19], [20], [21], [22]; SDGs 4 [6], [23], [24], [25], [26]; SDGs 5 [27], [28]; SDGs 7 [29], [30]; SDGs 8 [3], [8], [31], [32]; SDGs 9 [33]; SDGs 10 [34], [35]; SDGs 11. [36]; SDGs 12 [37], [38]; SDGs 13 [39], [40]; SDGs 14 [41], [42]; SDGs 16 [43]; and SDGs 17 [44].…”

An Ensemble-Based Multi-Classification Machine Learning Classifiers Approach to Detect Multiple Classes of Cyberbullying

“…Moreover, several experiments have emphasized that TF-IDF consistently outperforms other feature-extraction methods. In [33], the authors noted that TF-IDF achieved the highest accuracy in their approach compared to bag of words (BoW) feature extraction.…”

Sentiment analysis of global news on environmental issues: insights into public perception and its impact on low-carbon economy transition

“…This review stands out for its thorough examination of the application of sentiment analysis in environmental discourse, providing a roadmap for future research in this area. Sham and Mohamed (2022) proposed an innovative climate change sentiment analysis framework that leverages natural language processing techniques to analyze tweets related to climate change. Their research goes beyond mere analysis of sentiments; it also investigates the relationship between the sentiment polarity in tweets and socio-economic indicators of the countries where these tweets originated.…”