Papers › The Impact of an AirBnb Host's Listing Description 'Sentiment' and Length On Occupancy Rates
The Impact of an AirBnb Host's Listing Description 'Sentiment' and Length On Occupancy Rates
Richard Diehl Martinez, Anthony Carrington, Tiffany Kuo, Lena Tarhuni, Nour Adel Zaki Abdel-Motaal
The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.
There has been significant literature regarding the way product review sentiment affects brand loyalty. Intrigued by how natural language influences consumer choice, we were motivated to examine whether an AirBnb host's occupancy rate (how often their listing is booked out of the days they indicated their listing was available) can be determined by the perceived sentiment and length of their description summary. Our main goal, more generally, was to determine which features, including (but not limited to) sentiment and description length, most influence a host's occupancy rate. We define sentiment score through a natural language algorithm process, based on the AFINN dictionary. Using AirBnB data on New York City, our hypothesis is that higher sentiment scores (more positive descriptions) and longer summary length lead to higher occupancy rates. Our results show that while longer summary length may positively influence occupancy rates, more positive summary descriptions have no effect. Instead, we find that other factors such as number of reviews and number of amenities, in addition to summary length, are better indicators of occupancy rate.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections