Publication Date

Spring 2021

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science

First Advisor

Robert Chun

Second Advisor

Thomas Austin

Third Advisor

Gloria Yin


sentiment analysis, price prediction, regression trees


Airbnb is an online platform that provides arrangements for short-term local home renting services. It is a challenging task for the house owner to price a rental home and attract customers. Customers also need to evaluate the price of the rental property based on the listing details. This paper demonstrates several existing Airbnb price prediction models using machine learning and external data to improve the prediction accuracy. It also discusses machine learning and neural network models that are commonly used for price prediction. The goal of this paper is to build a price prediction model using machine learning and sentiment analysis techniques to help hosts and customers to price the house and evaluate the offered price. Other than using only the numerical data to build the model, customer review is another factor that affects the house pricing. Sentiment analysis techniques, such as Textblob, are also introduced in this project. Compared with using the numerical score of sentiment analysis from customer reviews, we classify sentiments into three types: positive, neutral, and negative. We observe that using classified sentiments with Regression Tree provides a more accurate prediction result compared with using numerical sentiment scores.