data quality, recommendation system, collaborative filtering, deep learning, text classification, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999

Research regarding collaborative filtering recommenders has grown fast lately. However, little attention has been paid to discuss how the input data quality impacts the result. Indeed, some review-rating pairs that a user gave to an item are inconsistent and express a different opinion, making the recommendation result biased. To solve the above drawback, this study proposes a two-phase deep learning-based recommender system. Firstly, a sentiment predictor of textual reviews is created, serving as the quality inspector that cleans and improves the input for a recommender. To build accurate predictors, this phase tries and compares a set of deep learning-based algorithms. Secondly, besides only exploiting the consistent review-rating pairs generated by the quality inspector, this phase builds deep learning-based recommender engines. The experiments on a real-world dataset showed the proposed data quality inspector, based on textual reviews, improves the overall performance of recommenders. On average, applying deep learning-based quality inspectors result in an above 6% improvement in RMSE, and more than a 2% boost in F1 score, and accuracy. This is robust evidence to prove the importance of the input data cleaning process in this field. Moreover, empirical evidence indicates the deep learning approach is suitable for modeling the sentiment predictor, and the core recommendation process, clearly outperforming the traditional machine learning methods.