Abstract

Floods have a significant socio-economic impact on Indonesian society. Much of this information is sourced from online news articles and social media. This research investigates whether the Support Vector Machine (SVM) method can be used for flood disaster level classification (low, medium, and high). Our methodology involves preparing data extracted from textual news articles on the National Disaster Management Agency (BNPB) website on the topic of flooding. We then labeled the data according to Regulation No. 02/2012 on general guidelines for disaster assessment and used the Support Vector Machine (SVM) method. Training and testing were conducted using different datasets, followed by accuracy and error evaluation. In addition, we considered the performance comparison of SVM with other classification methods, including Decision Tree, Naive Bayes, Adaboost, Random Forest, and Xgboost. The experimental results show that SVM still does not get good accuracy results for flood disaster level classification. The SVM accuracy level result of (52%) is still low compared to Random Forest (78%), and Xgboost (68%). Further research is expected to increase the accuracy of SVM for flood level classification.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call