Leveraging social media to gain insights into service delivery: a study on Airbnb
von Hoffen Moritz, Hagge Marvin, Betzing Jan Hendrik, Chasin Friedrich
Consumers increasingly rely on reviews and social media posts provided by others to get information about a service. Especially in the Sharing Economy, the quality of service delivery varies widely; no common quality standard can be expected. Because of the rapidly increasing number of reviews and tweets regarding a particular service, the available information becomes unmanageable for a single individual. However, this data contains valuable insights for platform operators to improve the service and educate individual providers. Therefore, an automated tool to summarize this flood of information is needed. Various approaches to aggregating and analyzing unstructured texts like reviews and tweets have already been proposed. In this research, we present a software toolkit that supports the sentiment analysis workflow informed by the current state-of-the-art. Our holistic toolkit embraces the entire process, from data collection and filtering to automated analysis to an interactive visualization of the results to guide researchers and practitioners in interpreting the results. We give an example of how the tool works by identifying positive and negative sentiments from reviews and tweets regarding Airbnb and delivering insights into the features of service delivery its users most value and most dislike. In doing so, we lay the foundation for learning why people participate in the Sharing Economy and for showing how to use the data. Beyond its application on the Sharing Economy, the proposed toolkit is a step toward providing the research community with an instrument for a holistic sentiment analysis of individual domains of interest.
Social media analysis; Sentiment analysis; Sharing Economy; Service delivery