Article
Computer Science, Information Systems
Rosmamalmi Mat Nawi, Shahrul Azman Mohd Noah, Lailatul Qadri Zakaria
Summary: By using LOD technology to address data sparsity issues beforehand, a GRS-LOD model was proposed. Experimental results indicated that the model, which utilized the Average strategy and individual profile aggregation approach, outperformed baseline studies in terms of prediction accuracy and relevancy.
Article
Computer Science, Information Systems
Samah Salem, Fouzia Benchikha
Summary: Data quality has long been a prominent issue in Linked Open Data (LOD), and this paper introduces a novel approach called LODQuMa to assess and improve the quality of LOD. It utilizes profiling statistics, synonym relationships, Quality Verification Cases (QVCs), and SPARQL query templates to enhance the quality dimensions of datasets.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Andre Levi Zanon, Leonardo Chaves Dutra da Rocha, Marcelo Garcia Manzato
Summary: This study improves the popularity bias and black box functioning in collaborative filtering algorithms by introducing a multi-domain item reordering system based on the best explanation for an item. The results indicate that this approach has shown promising outcomes in enhancing recommendation diversity and/or accuracy metrics.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Ricardo Dos Santos, Jose Aguilar
Summary: This research presents a hybrid recommender system that utilizes description/dialetheic logic and linked data to provide more precise recommendations and handle ambiguous information. It proposes a new architecture that integrates linked data into the recommender system and uses dialetheic logic to handle situations of contradiction or inconsistency.
Article
Computer Science, Information Systems
Hawre Hosseini, Ebrahim Bagheri
Summary: This paper investigates how implicit entities within social content can be identified and linked, introducing a method that models the problem as a learn to rank problem and includes appropriate features for identifying implicit entities. The results show that these features can improve the state of the art over the Precision at 1 metric.
INFORMATION PROCESSING & MANAGEMENT
(2021)
Article
Computer Science, Information Systems
Yu Du, Sylvie Ranwez, Nicolas Sutton-Charani, Vincent Ranwez
Summary: The diversity of item lists suggested by recommender systems significantly impacts user satisfaction. Existing diversity optimization approaches may not be effective for different recommendation approaches due to the diversity level of candidate lists depending on the recommender system used. Individual users' diversity needs are often ignored in post-processing diversification. This study systematically compares diversity performances of recommendation models in different domains and proposes a diversification post-processing objective that considers specific users' diversity needs.
INFORMATION PROCESSING & MANAGEMENT
(2021)
Article
Computer Science, Artificial Intelligence
Li-Yen Kuo, Chung-Kuang Chou, Ming-Syan Chen
Summary: The study introduces a personalized ranking framework for Poisson factorization that utilizes learning-to-rank based posteriori to optimize the ranking problem in recommender systems. By combining learning to rank and Poisson factorization, the framework performs well on sparse matrices and outperforms existing methods, as demonstrated in experiments.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Sumit Sidana, Mikhail Trofimov, Oleh Horodnytskyi, Charlotte Laclau, Yury Maximov, Massih-Reza Amini
Summary: This paper proposes a novel ranking framework for collaborative filtering, aiming to learn user preferences over items by minimizing a pairwise ranking loss, and derives a Neural-Network model for learning new representations of users and items along with preference relationships. Experimental results show that the model is suitable for implicit feedback data and competitive with state-of-the-art collaborative filtering techniques.
DATA MINING AND KNOWLEDGE DISCOVERY
(2021)
Article
Computer Science, Artificial Intelligence
Adolfo Ruiz-Calleja, Guillermo Vega-Gorgojo, Miguel L. Bote-Lorenzo, Juan Asensio-Perez, Yannis Dimitriadis, Eduardo Gomez-Sanchez
Summary: This paper proposes a template-based approach to semi-automatically create contextualized learning tasks, which bridge formal and informal learning. By applying this approach to the History of Art in the Spanish region of Castile and Leon, 16,000 learning tasks were generated and found to be aligned with classroom content by 85% of teachers. The tasks are available for access online.
JOURNAL OF WEB SEMANTICS
(2021)
Article
Computer Science, Information Systems
Hsin-Chang Yang, Chung-Hong Lee, Wen-Sheng Liao
Summary: This paper aims to incorporate data semantics into the measuring process by proposing methods to measure semantic distances between resources using information gathered from Linked Open Data (LOD), which were then applied to music recommendation. The experiments conducted using the MusicBrainz dataset showed that the proposed methods improved classic approaches for both linked data semantic distance (LDSD) and PathSim methods significantly.
DATA TECHNOLOGIES AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Pratik K. Biswas, Songlin Liu
Summary: In this paper, a hybrid recommender system that combines collaborative filtering with deep learning is proposed to enhance recommendation performance and overcome the limitations of collaborative filtering. By combining the outputs of collaborative filtering with a deep neural network in a big data processing framework, the proposed system outperforms existing hybrid recommender systems in recommending smartphones to prospective customers.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Theory & Methods
M. Mehdi Afsar, Trafford Crump, Behrouz Far
Summary: Recommender systems have become an integral part of our daily lives, helping us find our favorite items, friends on social networks, and movies to watch. The recommendation problem was traditionally seen as a classification or prediction problem, but it is now widely agreed that formulating it as a sequential decision problem using reinforcement learning can better capture user-system interaction and long-term engagement.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Artificial Intelligence
Niels Bertram, Juergen Dunkel, Ramon Hermoso
Summary: Music streaming platforms provide an overwhelming choice of music, and users rely on music recommendation systems to find music that suits their taste. This paper investigates how knowledge graph embeddings can enhance the quality of music recommendations by providing diverse and novel recommendations.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Hangbin Zhang, Raymond K. Wong, Victor W. Chu
Summary: The article introduces a novel recommender model called HVAE, which combines user and item information and utilizes collaborative filtering, showing superior performance compared to state-of-the-art models.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2022)
Review
Computer Science, Artificial Intelligence
Zhaoliang Chen, Shiping Wang
Summary: This paper provides an overview of recommender systems based on matrix completion, including the introduction of related algorithms, performance evaluation, and discussion of future research directions.
KNOWLEDGE AND INFORMATION SYSTEMS
(2022)