Sentiment analysis is crucial for understanding customer opinions and feedback. In this study, we compare the performance of two popular lexicon-based sentiment analysis tools: VADER (Valence Aware Dictionary and Sentiment Reasoner) and TextBlob. Our focus is on hotel reviews, a domain where accurate sentiment analysis is essential for businesses to enhance customer experiences. The main purpose of this study is to explore the potential of utilizing Social Big Data and text mining techniques to benefit stakeholders in the tourism and hospitality industry. We examine the impact of lexicon-based sentiment analysis approaches using VADER and TextBlob. Additionally, we investigate the performance of these tools across different hotel customer reviews. We begin by introducing VADER and TextBlob, highlighting their underlying methodologies and strengths. Next, we collect a dataset of hotel reviews from online platforms. After pre-processing the text data, we apply both tools to analyze sentiment polarity in the reviews. Our comparative evaluation involves metrics such as precision, recall, and f1-score. Preliminary results indicate that VADER demonstrates more consistent and reliable performance across different thresholds. It maintains high precision, recall, and accuracy, making it a more stable model for sentiment analysis. While TextBlob performs well at lower thresholds, its performance deteriorates at higher thresholds, particularly in terms of recall and accuracy. We discuss the implications of these findings for businesses seeking reliable sentiment analysis solutions. In conclusion, the VADER and TextBlob features discovered in this study provide valuable insights for sentiment analysis practitioners in the hospitality industry.