In this paper, we introduce a useful natural language model for improving recommendation systems using collaborative filtering algorithms on ordinal ratings data. Since their inception, recommendation systems have evolved from simple user-business-rating matrices to complex systems that can consume multiple dimensions. Using Yelp's competition data set, we explore extending these dimensions to include natural language by leveraging a dual neural network architecture to produce a new and improved star rating system which offers potential improvements to collaborative filtering based recommendation systems.
Kouvaris, Peter; Pirogova, Ekaterina; Sanadhya, Hari; Asuncion, Albert; and Rajagopal, Arun
"Text Enhanced Recommendation System Model Based on Yelp Reviews,"
SMU Data Science Review: Vol. 1:
3, Article 8.
Available at: https://scholar.smu.edu/datasciencereview/vol1/iss3/8
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License