Behavioural Indonesian disaster data classification in social media using KNN, random forest, and RNN in machine learning

Abstract

This research focuses on the classification of Indonesian disaster data extracted from social media using three distinct machine learning models: K-Nearest Neighbors (KNN), Random Forest, and Recurrent Neural Network (RNN). The study evaluates and compares the performance of these models based on accuracy metrics. The KNN model demonstrates competency with an 82% accuracy, showcasing its ability to handle data based on nearest neighbors. However, there are indications of potential limitations in handling complex patterns or high-dimensional datasets. In contrast, Random Forest achieves a notable 94% accuracy, highlighting its effectiveness in combining decision trees to enhance performance and mitigate overfitting. The RNN model exhibits the highest performance, achieving 96% accuracy, attributed to its proficiency in understanding temporal relationships and sequential patterns in data, making it a robust choice for sequential datasets such as text or time series. The findings underscore the importance of selecting models tailored to specific dataset characteristics and desired classification analyses. Furthermore, future research directions involve exploring adaptations or optimizations of these models for diverse disaster types and social media data, aiming to develop more sophisticated and responsive models for disaster-related analysis in the Indonesian context.