This thesis investigates the optimization of Airbnb operations in Singapore through a detailed analysis of guest preferences using K-means clustering and aspect-based sentiment analysis. The primary objectives of the study are to understand guest pref...
This thesis investigates the optimization of Airbnb operations in Singapore through a detailed analysis of guest preferences using K-means clustering and aspect-based sentiment analysis. The primary objectives of the study are to understand guest preferences, identify key aspects influencing guest satisfaction, and provide actionable insights for Airbnb hosts. By systematically analyzing guest reviews of Airbnb listings in Singapore, the study employs K-means clustering to categorize listings into distinct clusters based on similarities in their features, thus revealing the diverse needs and preferences of different guest segments.
The research identifies and evaluates specific aspects of Airbnb listings, such as accuracy, amenities, check-in process, comfort, communication, family-friendliness, host interaction, location, maintenance and condition, neighborhood, and value, which significantly impact guest satisfaction. By pinpointing the most influential aspects, hosts can allocate resources more effectively and address critical areas needing enhancement. The findings are translated into practical recommendations that hosts can implement to optimize their listings and improve guest satisfaction, guiding them in making informed decisions that enhance their operational strategies, leading to better guest reviews and increased bookings.
Key outcomes of this analysis include ensuring accuracy in listing descriptions to align with guest expectations, enhancing the check-in process with clear instructions and flexible options, improving communication through timely responses and proactive engagement, offering good value by competitively pricing listings and highlighting unique features, focusing on host interaction by being approachable and providing personalized touches, and investing in comfort and amenities to maintain and upgrade quality furnishings and essential amenities regularly.
Furthermore, hosts will gain a strategic framework to optimize their listings based on identified guest preferences and sentiment trends, which includes personalizing guest experiences, leveraging positive aspects highlighted by guests, and creating unique selling propositions. Insights from this study contribute to a broader understanding of guest preferences and behaviors within the Singaporean Airbnb market, providing data-driven evidence to support policy decisions regarding short-term rentals, offering benchmarks for other hosts to evaluate and improve their listings, and encouraging higher standards of service and quality across the Airbnb community.