Article
Computer Science, Artificial Intelligence
Donghua Liu, Jia Wu, Jing Li, Bo Du, Jun Chang, Xuefei Li
Summary: This paper proposes a novel Adaptive Hierarchical Attention-enhanced Gated network (AHAG) for item recommendation. AHAG captures the hidden intentions of users by adaptively incorporating reviews. Experimental results show that AHAG significantly outperforms state-of-the-art methods and the attention mechanism increases the interpretability of the recommendation task.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Mathematics
Sundaresan Bhaskaran, Raja Marappan, Balachandran Santhi
Summary: Different recommendation techniques in e-learning have been designed to provide personalized learning experiences for learners based on their needs and interests. Research shows that a clustering recommender system based on split and conquer strategy has been successful in experiments with different groups and datasets, improving recommendation performance.
Article
Computer Science, Information Systems
Ning Liu, Jianhua Zhao
Summary: In this paper, a recommendation system based on sentiment analysis and matrix factorization (SAMF) is proposed to solve the problems of data sparsity and credibility in collaborative filtering. By utilizing topic model and deep learning technology, the implicit information in reviews is fully mined to improve the rating matrix and assist in recommendation.
Article
Computer Science, Artificial Intelligence
Shengyu Zhang, Fuli Feng, Kun Kuang, Wenqiao Zhang, Zhou Zhao, Hongxia Yang, Tat-Seng Chua, Fei Wu
Summary: The paper investigates the interactions between latent factors in recommender systems and proposes a personalized latent structure learning framework called PlanRec. It personalizes the universally learned dependencies through probabilistic modeling and balances shared knowledge and personalization through uncertainty estimation.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Martin Pichl, Eva Zangerle
Summary: As music consumption has shifted towards music streaming platforms in the past decade, users are increasingly relying on music recommender systems to help them discover music they like due to the overwhelming amount of choices available.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Business
Minsung Hong, Jason J. Jung
Summary: ClustPTF is a clustering-based parallel tensor factorization method that uses sentiment analysis and K-means clustering to improve recommendation diversity and predictive performance. Experimental results show that ClustPTF significantly outperforms traditional methods in recommendation diversity and response time, while also achieving significant improvements in predictive performance.
ELECTRONIC COMMERCE RESEARCH AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Yongsen Zheng, Pengxu Wei, Ziliang Chen, Yang Cao, Liang Lin
Summary: We propose an effective neural recommender system called graph-convolved factorization machine (GCFM), which extends feature interactions from pairs to neighbors, capturing more comprehensive and explainable information while reaping the advantages of representation learning. GCFM significantly outperforms state-of-the-art algorithms and shows interpretability in recommendation tasks.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Review
Computer Science, Information Systems
Mehdi Elahi, Danial Khosh Kholgh, Mohammad Sina Kiarostami, Mourad Oussalah, Sorush Saghari
Summary: Hybrid recommender systems use advanced algorithms to learn from different types of data and provide personalized recommendations for users. Previous studies have mainly relied on ratings as user feedback, but they may not capture the full picture of user preferences. This paper proposes a hybrid recommender system that analyzes reviews and extracts sentiments to improve the recommendation process.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Tianjun Wei, Tommy W. S. Chow, Jianghong Ma
Summary: This article proposes a correlation-aware review aspect recommender (CARAR) system model that can make personalized recommendations by constructing self-representation correlations between different views of review aspects. The model can identify and utilize dependencies between different aspects and enhance recommendation performance through cross-view correlation mapping. Experimental results demonstrate the effectiveness of the approach in review aspect recommendation tasks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yuan-Yuan Xu, Shen-Ming Gu, Fan Min
Summary: This paper proposes an efficient and effective outlier removal algorithm to improve the quality of training data. By modeling the noise as a mixture of Gaussian distribution and calculating low-rank matrices, the algorithm compares the original and recovered ratings to identify suspected outliers.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Chen Gao, Nian Li, Tzu-Heng Lin, Dongsheng Lin, Jun Zhang, Yong Li, Depeng Jin
Summary: Social recommendation, although widely utilized in enhancing recommender systems, often assumes a uniform influence of social relationships, which is not reflective of the fact that users may have diverse preferences with different friends. In this paper, the CSR model is proposed to address this issue by introducing a universal regularization term that captures the varying social influence. Experimental results demonstrate the superiority of the CSR model over existing social recommendation methods, particularly for users with sparse social relations or behavioral interactions.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Information Systems
Shulin Cheng, Huimin Jiang, Wanyan Wang, Wei Jiang
Summary: Compared to traditional recommender systems, context-aware recommender systems are better suited to real-world application contexts. However, most existing research has focused on single context-aware recommendations, such as time or location, and lacks in-depth analysis of multi-context-aware recommendations. Therefore, we proposed a high-order tensor factorization recommendation method based on multi-context awareness. By detecting user sensitivity to multiple contexts and constructing four-dimensional tensors and feature matrices, we were able to effectively address data sparsity. Our method improved recommendation quality through parameter optimization and filling in missing data, and was validated using a multi-context-aware movie dataset.
MULTIMEDIA SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Junrui Liu, Zhen Yang, Tong Li, Di Wu, Ruiyi Wang
Summary: This paper proposes a novel personalized recommendation method called similarity pairwise ranking (SPR) to address the issue of imbalanced data distribution affecting the effectiveness of Bayesian personalized ranking (BPR). By eliminating the score differences between popular and personalized items based on their similarity, SPR enhances the recommendation quality and better meets the individual needs of users. Experimental results demonstrate the superiority of SPR over recent state-of-the-art methods.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Nabila Amir, Fouzia Jabeen, Zafar Ali, Irfan Ullah, Asim Ullah Jan, Pavlos Kefalas
Summary: This survey fills the gap in the literature by summarizing the strengths, weaknesses, and trends of news recommendation models employing DL methods. It also discusses the commonly used datasets, evaluation methods, and implications for researchers in this area.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Information Systems
Naina Yadav, Sukomal Pal, Anil Kumar Singh, Kartikey Singh
Summary: This paper introduces the collaborative filtering method for recommender systems, but points out the issues in diversity and coverage. To address this problem, the authors propose a cluster-based diversity recommendation method, which utilizes different clustering techniques and pre-trained models for generating diverse recommendations.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)