Sentiment Analysis of Visitor Reviews on Google Maps at Kampung Coklat Tourism

Google Maps plays an important role in the tourism industry, allowing visitors to share their reviews widely. These reviews not only influence potential visitors' decisions but also impact the reputation of tourist destinations. However, evaluating service quality based on offline reviews remains suboptimal compared to online reviews, which are more accessible and interpretable. This research focuses on sentiment analysis of visitor reviews on Kampung Coklat in Blitar using the Naïve Bayes algorithm. The goal is to classify reviews into positive, neutral, or negative to understand visitors' perspectives on the tourism services. Data was collected from Google Maps and processed using the Naïve Bayes method, which has proven effective in sentiment classification even with relatively small training data sets. Experimental results showed the highest accuracy of 75% with an 80% training data and 20% testing data ratio. WordCloud analysis also depicts frequently occurring words in positive, neutral, and negative reviews, providing insights into aspects influencing tourists' experiences.