Enhancing Yelp Data with Deep Learning and Information Reuse
Roberto Camacho Barranco, Laura Rodríguez, Rebecca Urbina, Mahmud Shahriar Hossain · 2017
Crowd-sourced reviews are used daily by potential customers to learn relevant information about a business. While textual reviews have become prominent in many recommendation-based systems, the inclusion of images can significantly increase the effectiveness of a review. However, it is difficult to verify the accuracy and usefulness of the information provided by a contributing user. In this paper, we address this issue by proposing a deep-learning-based information-reuse framework to automatically: (1) tag the images available in a review dataset, (2) generate a caption for each image that does not have one, and (3) enhance each review through information reuse by automatically mapping reviews to existing relevant images. We evaluate the proposed framework using the data made available for the Yelp Dataset Challenge. The results indicate that the proposed framework provides high-quality enhancements through automatic captioning, tagging, and recommendation for mapping reviews and images.