Social Media Sentiment Analysis for Local Water Company Customers Using a Support Vector Machine Algorithm

The United Nations under the WMO predicts that more than 5 billion people will experience a water crisis in 2050. PDAM is responsible for managing drinking water, which is one of the government's efforts to prevent a water crisis in Indonesia. However, only 17.96% of all household heads in Indonesia use PDAM. PDAM uses Facebook and Instagram accounts to interact and convey information to its users. In this study an analysis of the sentiments of PDAM users regarding the services provided will be carried out. The information used came from online scraping of PDAM social media accounts. The algorithm used is Support Vector Machine with the words TF-IDF and SMOTE as weighted as imbalanced data handling. After experimenting with the best holdout modelling method, the ratio of 70:30 on balanced data with negative label data has a precision value of 0.95, recall of 0.99 and f1-score of 0.97. Meanwhile, data with a positive label has a precision value of 0.90, a recall of 0.62 and an fl-score of 0.73. The accuracy value is 95% and has an AUC value of 0.927. The results of the analysis show that many PDAM users have complaints related to water services that often fail, payments, leaks, cloudy water, and meter records.