Analyzing Tweets to Understand Factors Affecting Opinion on Climate Change
29 Jan 2021-pp 99-110
TL;DR: In this article, the authors study people's opinion on climate change and analyze the data to identify the common topics which garner discussion and derive the possible explanation in terms of different factors.
Abstract: Climate change is a topic that is frequently debated on social media A vast majority in the debate cite scientific evidence to recognize the existence of a man-made climate change and its impacts on environment as well as society The opinion of the masses is critical to dealing with various issues arising due to climate change, such as global warming In this work, we study people’s opinion on climate change and analyze the data to identify the common topics which garner discussion Our aim is to analyze the dataset, explore the popular belief of a region and then derive the possible explanation in terms of different factors This analysis could help us in determining the extent to which different factors affect people’s opinion By building sentiment analysis models, performing topic modelling and using other appropriate technologies, we can visualise the sentiment pattern to understand the factors affecting them
References
More filters
01 Jan 2007
TL;DR: random forests are proposed, which add an additional layer of randomness to bagging and are robust against overfitting, and the randomForest package provides an R interface to the Fortran programs by Breiman and Cutler.
Abstract: Recently there has been a lot of interest in “ensemble learning” — methods that generate many classifiers and aggregate their results. Two well-known methods are boosting (see, e.g., Shapire et al., 1998) and bagging Breiman (1996) of classification trees. In boosting, successive trees give extra weight to points incorrectly predicted by earlier predictors. In the end, a weighted vote is taken for prediction. In bagging, successive trees do not depend on earlier trees — each is independently constructed using a bootstrap sample of the data set. In the end, a simple majority vote is taken for prediction. Breiman (2001) proposed random forests, which add an additional layer of randomness to bagging. In addition to constructing each tree using a different bootstrap sample of the data, random forests change how the classification or regression trees are constructed. In standard trees, each node is split using the best split among all variables. In a random forest, each node is split using the best among a subset of predictors randomly chosen at that node. This somewhat counterintuitive strategy turns out to perform very well compared to many other classifiers, including discriminant analysis, support vector machines and neural networks, and is robust against overfitting (Breiman, 2001). In addition, it is very user-friendly in the sense that it has only two parameters (the number of variables in the random subset at each node and the number of trees in the forest), and is usually not very sensitive to their values. The randomForest package provides an R interface to the Fortran programs by Breiman and Cutler (available at http://www.stat.berkeley.edu/ users/breiman/). This article provides a brief introduction to the usage and features of the R functions.
14,830 citations
21 Apr 1998
TL;DR: This paper explores the use of Support Vector Machines for learning text classifiers from examples and analyzes the particular properties of learning with text data and identifies why SVMs are appropriate for this task.
Abstract: This paper explores the use of Support Vector Machines (SVMs) for learning text classifiers from examples. It analyzes the particular properties of learning with text data and identifies why SVMs are appropriate for this task. Empirical results support the theoretical findings. SVMs achieve substantial improvements over the currently best performing methods and behave robustly over a variety of different learning tasks. Furthermore they are fully automatic, eliminating the need for manual parameter tuning.
8,658 citations
21 Jun 2000
TL;DR: Some previous studies comparing ensemble methods are reviewed, and some new experiments are presented to uncover the reasons that Adaboost does not overfit rapidly.
Abstract: Ensemble methods are learning algorithms that construct a set of classifiers and then classify new data points by taking a (weighted) vote of their predictions. The original ensemble method is Bayesian averaging, but more recent algorithms include error-correcting output coding, Bagging, and boosting. This paper reviews these methods and explains why ensembles can often perform better than any single classifier. Some previous studies comparing ensemble methods are reviewed, and some new experiments are presented to uncover the reasons that Adaboost does not overfit rapidly.
5,679 citations
TL;DR: In this article, the authors published a paper entitled "Oceanography 22 no. 4 (2009): 36-47", which is a summary of the Oceanography 22 No. 4 issue.
Abstract: Author Posting. © Oceanography Society, 2009. This article is posted here by permission of Oceanography Society for personal use, not for redistribution. The definitive version was published in Oceanography 22 no. 4 (2009): 36-47.
908 citations
TL;DR: In this article, the authors argue that evaluating the relation between transforming communication technologies and collective action demands recognizing how such technologies infuse specific protest ecologies, and that traces of these media may reflect larger organizational schemes.
Abstract: The Twitter Revolutions of 2009 reinvigorated the question of whether new social media have any real effect on contentious politics. In this article, the authors argue that evaluating the relation between transforming communication technologies and collective action demands recognizing how such technologies infuse specific protest ecologies. This includes looking beyond informational functions to the role of social media as organizing mechanisms and recognizing that traces of these media may reflect larger organizational schemes. Three points become salient in the case of Twitter against this background: (a) Twitter streams represent crosscutting networking mechanisms in a protest ecology, (b) they embed and are embedded in various kinds of gatekeeping processes, and (c) they reflect changing dynamics in the ecology over time. The authors illustrate their argument with reference to two hashtags used in the protests around the 2009 United Nations Climate Summit in Copenhagen.
534 citations