Disaggregate Hotel Evaluation by Using Diverse Aspects from User Reviews

TitleDisaggregate Hotel Evaluation by Using Diverse Aspects from User Reviews
Publication TypeConference Proceedings
Year of Conference2019
AuthorsDevkota, B, Kim, K, Zhuang, C, Miyazaki, H
Conference Name2019 IEEE International Conference on Big Data and Smart Computing (BigComp)
Date PublishedFeb
KeywordsAdaptation models, aspects, Coherence, coherent hotel aspects, customer satisfaction, data mining, Data models, disaggregate hotel evaluation, diverse aspects, Estimation, Feature extraction, fine-grained aspect level opinions, frequent noun-adjective co-occurrence statistics, hotel industry, hotel ranking, hotel reviews, latent aspects, Predictive models, purchase decision, statistical analysis, supervised methods, topic modeling, unsupervised learning, user attention, user reviews, word co-occurrence statistics, word embeddings

Experienced opinions about products and services can guide a potential user for a better purchase decision. Fine-grained aspect level opinions embedded within reviews must be explored to discover experienced users' latent opinion about the aspects (i.e. features of products like cost, value for money, etc.) and their relative importance. In this paper, we present an unsupervised approach for discovering coherent hotel aspects based on the user attention. This model effectively integrates techniques like topic modeling and word embeddings along with the frequent noun-adjective co-occurrence statistics to automatically discover coherent hotel aspects. Further supervised methods are used to understand the user's relative emphasis on the aspects and finally rank the hotels. This method does not assume any predefined seed words and discovers coherent level aspects by directly using user attention and word co-occurrence statistics in addition to topic modeling and word embeddings. The performance evaluation of this method was done by collecting various hotel reviews from multiple travel websites. Results show that the proposed methods improved the baseline performance up to 90%. Hence, the results thus obtained are very promising and indicate that the system is simple, scalable and most of all accurate in ranking hotels based on the latent aspects expressed in the user reviews.