Abstract
Purpose – This paper aims to investigate attributes that influence Airbnb customer experience by analysing online reviews from users staying in London. It presents a text mining approach to identify a set of broad themes from the textual reviews. It aims to highlight the customers’ changing perception of good quality of accommodations.
Design/methodology/approach – This paper analyses 169,666 reviews posted by Airbnb
users who stayed in London from 2011 to 2015. Hierarchical clustering algorithms are used to
group similar words into clusters based on their co-occurrence. Longitudinal analysis and
seasonal analysis are conducted for a more coherent understanding of the Airbnb customer
behaviour.
Findings – This paper provides empirical insights about how Airbnb users’ mind-set of good quality of accommodations changes over a 5-year timespan and in different seasons. While
there are common attributes considered important throughout the years, exclusive attributes are discovered in particular years and seasons.
Research limitations/implications – This paper is confined to Airbnb experiences in London.
Researchers are encouraged to apply the proposed methodology to investigate Airbnb
experiences in other cities and detect any change in customer perception of quality stay.
Practical implications – This paper offers implications for the prioritisation of customer
concerns to design and improve services offerings and for alignment of services with customer expectations in the sharing economy.
Originality/value – This paper fulfils an identified need to examine the change in customer expectation across the timespan and seasons in the case of Airbnb. It also contributes by illustrating how big data can be used to uncover key attributes that facilitate the engagement with the sharing economy.
Design/methodology/approach – This paper analyses 169,666 reviews posted by Airbnb
users who stayed in London from 2011 to 2015. Hierarchical clustering algorithms are used to
group similar words into clusters based on their co-occurrence. Longitudinal analysis and
seasonal analysis are conducted for a more coherent understanding of the Airbnb customer
behaviour.
Findings – This paper provides empirical insights about how Airbnb users’ mind-set of good quality of accommodations changes over a 5-year timespan and in different seasons. While
there are common attributes considered important throughout the years, exclusive attributes are discovered in particular years and seasons.
Research limitations/implications – This paper is confined to Airbnb experiences in London.
Researchers are encouraged to apply the proposed methodology to investigate Airbnb
experiences in other cities and detect any change in customer perception of quality stay.
Practical implications – This paper offers implications for the prioritisation of customer
concerns to design and improve services offerings and for alignment of services with customer expectations in the sharing economy.
Originality/value – This paper fulfils an identified need to examine the change in customer expectation across the timespan and seasons in the case of Airbnb. It also contributes by illustrating how big data can be used to uncover key attributes that facilitate the engagement with the sharing economy.
| Original language | English |
|---|---|
| Number of pages | 17 |
| Journal | Information Technology and People |
| DOIs | |
| Publication status | Published - 30 Jul 2019 |
Keywords
- online review
- consumer behaviour
- text mining
- sharing economy
- Airbnb
Access to Document
- Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via Emerald Insight at https://doi.org/10.1108/ITP-10-2018-0475 . Please refer to any applicable terms of use of the publisher.