The rise of the sharing economy has disrupted traditional industries, and Airbnb stands out as one of the most popular platforms in this space. With over 2 million people staying on Airbnb every night, it has become a viable alternative to hotels for travelers worldwide. This online peer-to-peer platform allows hosts to offer their spare rooms or properties to guests, creating a unique and personalized accommodation experience. However, in such a competitive industry, service quality plays a crucial role in gaining a competitive advantage. Customer satisfaction is directly linked to service quality, making it a key success factor for businesses. In the era of the fourth industrial revolution, known as Industry 4.0, quality management has evolved to adapt to technological innovations. This has given rise to a new paradigm called Quality 4.0, which emphasizes the use of big data analytics and technology-driven solutions in quality management.
Understanding the importance of customer feedback and insights, businesses are turning to user-generated content, such as customer reviews, to gather valuable information. Airbnb, being a digital platform, has accumulated a vast amount of user reviews, with over 250 million reviews written by hosts and guests from around the world. Analyzing this large volume of unstructured textual data manually is beyond human capacity. However, text mining, a data analysis technique, offers an efficient way to extract actionable insights from these reviews and ratings.
Objective of the Study
The objective of this study is twofold. Firstly, it aims to identify the main service quality attributes mentioned in Airbnb reviews. Secondly, it seeks to determine which attributes have a positive or negative correlation with the user's sentiment. By achieving these objectives, the study aims to shed light on the relationship between service quality attributes and customer satisfaction. Additionally, it contributes to the literature on Quality 4.0 by demonstrating a practical application of big data analytics in quality management.
Methodology
To achieve the research objectives, the study combines two text mining techniques: sentiment analysis and topic modeling. Sentiment analysis is used to assign a sentiment score to each review, indicating the polarity and intensity of the emotions expressed by the user. Topic modeling, specifically the Structural Topic Model (STM), is applied to identify underlying topics and their weights in each review. The study uses a dataset of 2,735,437 Airbnb reviews from four European countries: France, Italy, Spain, and Portugal.
Results and Implications
The study identifies 37 service quality attributes related to Airbnb based on the analysis of the reviews. These attributes span across dimensions such as host service quality, web responsiveness quality, web efficiency quality, and facility service quality. Out of these attributes, eight showed a statistically significant correlation with the sentiment score. Among the positive attributes were views, host tips and advice, location, and host friendliness. On the other hand, negative attributes included sleep disturbance, website responsiveness, thermal management, and hygiene issues. By understanding the relationship between these attributes and customer sentiment, businesses can prioritize improvements and enhance the overall guest experience.
The study contributes to the literature on Quality 4.0 by showcasing a practical implementation of big data analytics in quality management. It demonstrates how user-generated content, such as Airbnb reviews, can be leveraged to gain insights into service quality and drive improvements. The findings also expand the existing knowledge on service quality in peer-to-peer accommodation services, with a focus on European Airbnb users. Future research opportunities include exploring other platforms in the sharing economy, analyzing country-specific guest preferences, and studying the evolution of service attributes over time.
Conclusion
The study highlights the importance of service quality in the sharing economy, particularly in the context of Airbnb. By analyzing a vast amount of user-generated content, businesses can gain valuable insights into customer preferences and sentiment. This study demonstrates the effectiveness of text mining techniques, such as sentiment analysis and topic modeling, in extracting actionable insights from large-scale databases of reviews and ratings. The findings contribute to the evolving field of Quality 4.0 and provide practical implications for businesses in the hospitality industry. As the sharing economy continues to grow, it is crucial for businesses to adapt to technological advancements and leverage big data analytics to improve service quality and enhance customer satisfaction.
Reference
Amat-Lefort N.; Barravecchia F.; Mastrogiacomo L. (2023). Quality 4.0: big data analytics to explore service quality attributes and their relation to user sentiment in Airbnb reviews. International Journal of Quality and Reliability Management, 40(4), 990-1008, DOI: 10.1108/IJQRM-01-2022-0024.