Understanding Fine-Grained Sentiments of Super-Priority Destination Visitors using Multi-task Learning for Extraction of Aspect Terms and Polarity Classification on Reviews

Abstract

One sector that plays an important role in the national economy is the Tourism sector. To maintain economic stability, the Indonesian Government has made various efforts to mitigate the impact of the Covid-19 pandemic on the tourism sector. The National Economic Recovery (PEN) is one of its programs, specifically focused on the recovery of tourism, particularly in the 5 super-priority destinations (Lake Toba, Borobudur, Mandalika, Labuan Bajo, Likupang). To ensure the effective recovery of these 5 super-priority destinations, in addition to information from stakeholders, the government can conduct studies based on the aspirations of the people. One task that can assist the government in summarizing user reviews is sentiment analysis. Previous studies have focused on comments from the local Indonesian population, which have not reached the majority of tourists who comment in English. Therefore, there is a need for Sentiment Analysis (SA) at the aspect level on TripAdvisor reviews of the Super Priority Destinations (SPDs) using the English language. The method used for sentiment analysis of these tourist reviews is the Local Context Focus - Aspect Term Extraction & Aspect Polarization Classification (LCF-ATEPC). This method employs multi-task learning, domain Bidirectional Encoder Representations from Transformers (BERT), and information about the aspect position within a sentence. Based on the research, the LCF-ATEPC model has proven to be capable of performing sentiment analysis of English aspects effectively. The best-performing LCF-ATEPC model was obtained using a dataset without outliers (95%) with APC-ACC, APC-F1, and ATE-F1 accuracies of 83.33%, 69.5%, and 66.83%, respectively.