Transformer-based Information Extraction from Twitter Text on Complaint Monitoring System

Abstract

Customer complaints receive more attention from a company because bad handling of complaints will cause the loss of existing customers. Current customers tend to use social media to report complaints by including information on the location of the complaint so that the location also needs to be extracted because it can be authentic geographic evidence in the complaint monitoring system. The number of complaint reports via social media is increasing occasionally, making the manual complaint monitoring system very inefficient because it takes a long time. This study proposes an automatic complaint monitoring system on Indonesian text from Twitter by extracting transformer-based information. The automatic complaint monitoring system uses a combination of the Bidirectional Encoder Representation from Transformer (BERT) model to extract location information on complaint tweets and the Convolutional Neural Network (CNN) model to classify the complaint type, which gets the highest F1 score of 0.90471. The complaint monitoring system is also visualized in the complaint locations to make it easier for companies to find the location of complaint reports, and action can be taken to deal with public complaints immediately.