| 作成者 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 本文言語 |
|
| 出版者 |
|
|
|
| 発行日 |
|
| 収録物名 |
|
| 巻 |
|
| 号 |
|
| 開始ページ |
|
| 終了ページ |
|
| 出版タイプ |
|
| アクセス権 |
|
| Crossref DOI |
|
| 権利関係 |
|
| 概要 |
Single-use plastics have become an urgent global environmental concern. The Indonesian government has attempted to introduce a policy that bans the use of single-use plastics as an initial step toward... overcoming this issue. However, policy implementation often faces challenges from stakeholders. Therefore, this study aims to analyze public sentiment expressed on the X platform (formerly known as “Twitter”) regarding the policy of banning single-use plastic bags in Indonesia. The methods used in this study include data collection, pre-processing (cleaning and transforming), labeling, modeling, and analysis using RapidMiner software. Tweet data were then analyzed using three machine learning methods, i.e., Naïve Bayes, K-Nearest Neighbors (KNN), and Decision Tree. Data were divided into training and test sets with a ratio of 60:40, 70:30, and 80:20. As many as 1038 refined datasets from 2019-2023 with related keywords were obtained. Based on the performance evaluation, the Naïve Bayes algorithm can improve its performance as the amount of training data increases, without overfitting. This algorithm achieves the highest accuracy of 89.73% at an 80:20 ratio. Furthermore, the classification results of the majority (70.6%) of the tweets showed positive support for the policy, 19.6% were negative, and 9.8% were neutral. In other words, the results of this sentiment classification can be used to monitor public responses and formulate environmentally friendly policies that are effective and supported by the majority.続きを見る
|
Mendeley出力
