Assessing Guest Nationality Composition from Hotel Reviews
This provides incremental value for hotel competitors, suppliers, researchers, and the general public by enabling dynamic assessment of guest composition from reviews.
The paper tackled the problem of estimating guest nationality composition for individual hotels, which lacks fine-grained data, by using machine learning to extract nationality references from unstructured text reviews. They demonstrated that a simple architecture with pre-trained embeddings and stacked LSTM layers achieved a better performance-runtime tradeoff than more complex state-of-the-art language models.
Many hotels target guest acquisition efforts to specific markets in order to best anticipate individual preferences and needs of their guests. Likewise, such strategic positioning is a prerequisite for efficient marketing budget allocation. Official statistics report on the number of visitors from different countries, but no fine-grained information on the guest composition of individual businesses exists. There is, however, growing interest in such data from competitors, suppliers, researchers and the general public. We demonstrate how machine learning can be leveraged to extract references to guest nationalities from unstructured text reviews in order to dynamically assess and monitor the dynamics of guest composition of individual businesses. In particular, we show that a rather simple architecture of pre-trained embeddings and stacked LSTM layers provides a better performance-runtime tradeoff than more complex state-of-the-art language models.