A Computational Approach to Perceived Trustworthiness of Airbnb Host Profiles

Xiao Ma, Trishala Neeraj, Mor Naaman

May 15, 2017 -
paper icwsm

[Preprint]
Proceedings of the 11th International AAAI Conference on Web and Social Media (ICWSM-17)

[Dataset] on Github

Poster

poster

Demo application:

  • Profer
    • Profer: an Airbnb host prof(ile-analyz)er.
    • Built with Flask with our pre-trained model using the dataset.

profer example

Research behind the demo

Building on our previous work, we developed a novel computational framework to predict the perceived trustworthiness of host profile texts in the context of online lodging marketplaces. To achieve this goal, we developed a dataset of 4,180 Airbnb host profiles annotated with perceived trustworthiness. To the best of our knowledge, the dataset along with our models allow for the first computational evaluation of perceived trustworthiness of textual profiles, which are ubiquitous in online peer-to-peer marketplaces. We provide insights into the linguistic factors that contribute to higher and lower perceived trustworthiness for profiles of different lengths.

Computational model