Sentiment Analysis of Shared Tweets on Global Warming on Twitter with Data Mining Methods: A Case Study on Turkish Language

Abstract

As the usage of social media has increased, the size of shared data has instantly surged and this has been an important source of research for environmental issues as it has been with popular topics. Sentiment analysis has been used to determine people's sensitivity and behavior in environmental issues. However, the analysis of Turkish texts has not been investigated much in literature. In this article, sentiment analysis of Turkish tweets about global warming and climate change is determined by machine learning methods. In this regard, by using algorithms that are determined by supervised methods (linear classifiers and probabilistic classifiers) with trained thirty thousand randomly selected Turkish tweets, sentiment intensity (positive, negative, and neutral) has been detected and algorithm performance ratios have been compared. This study also provides benchmarking results for future sentiment analysis studies on Turkish texts.

Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data

“…Kaya [58] It analyzes the sentiment of Turkish political news using a transfer learning approach. Kirelli et al [11] It determines the sentiment of Turkish tweets on global warming and climate change. Onder [59] It determines both positivity and negativity of Turkish tweets from a transportation company to analyze customer satisfaction.…”

“…As an extra factor, questions remain as to whether the achieved accuracy will remain the same if each sentence in a document is considered separately. In a different direction, Kirelli et al [11] performed sentiment analysis of shared Turkish tweets on global warming and climate change with data mining methods.…”

Topic Modelling and Sentiment Analysis of Global Warming Tweets

“…), exclamation point (!) and special characters such as ampersand (&), slash (/), backslash (\), and the tilde (~), which are uninformative in text-mining based on bag-of-words (Kirelli & Arslankaya, 2020;Maier et al, 2018). Following that, the removal of stop words (e.g., articles, prepositions) is necessary since stop words bear no specific meaning thus have little contribution to the document content (Mustaqim et al, 2020).…”

Intensity quantification of public opinion and emotion analysis on climate change

“…Kirelli and Arslankaya [19] performed sentiment analysis on Turkish texts to understand society's receptivity towards climate change, integrating various machine learning techniques such as NB, SVM, K-Nearest Neighbor (KNN) for improvement in the accuracy and performance measures. However, this study only included Turkish texts as part of the conducted analysis.…”