Aspect based hotel recommendation system using dilated multichannel CNN and BiGRU with hyperbolic linear unit

• Published in: International journal of machine learning and cybernetics Vol. 15; no. 11; pp. 4867 - 4886
• Main Authors: Jai Arul Jose, G., Mastan, Mahammad, Al-Nuaimy, Louay A. Hussein
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2024; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Artificial neural networks; Clustering; Cold; Collaboration; Complex Systems; Computational Intelligence; Control; Engineering; Hotels & motels; Mechatronics; Neural networks; Original Article; Pattern Recognition; Recommender systems; Robotics; Semantics; Sparsity; Systems Biology; Attention mechanism; And bi-directional gated recurrent unit; Dilated convolutional neural network; Recommendation system
• ISSN: 1868-8071; 1868-808X
• DOI: 10.1007/s13042-024-02184-6

In recent years, the recommendation system has become one of the important tools of e-commerce, which provides suggestions to the user for some resources such as hotels, songs, books, movies, etc. The existing hotel recommendation method has faced many problems such as data sparsity, cold-start problems, scalability, etc. Traditional Convolutional Neural Networks (CNNs) often struggle to capture long-term semantic characteristics, and their variants, such as Dilated CNNs, may encounter issues with gradient exploding. Moreover, Gated Recurrent Units (GRUs) and Bidirectional GRUs, while effective in capturing context information, may suffer from low learning efficiency and convergence challenges. Hence, this paper proposes the hotel recommendation system to use the hybrid of dilated multichannel convolutional neural network (MCNN) and bi-directional gated recurrent unit (BiGRU) with an attention mechanism. The main aim of this research is to develop a more efficient, scalable, regularized, and generalized recommendation system which can recommend the name of the hotels to the travellers based on their preferences by analysing the previous so far traveller’s comments together with the rating value to improve the forecast accuracy. The aspect based attention mechanisms are employed to evaluate the word, sentence, and semantic level similarity weight based vectors for mining useful information. The proposed approach has shown improved performance than existing approaches in terms of 99.46% Accuracy, 98.94% Precision, 98.84% Recall, and 98.75% F1-score.