Article
Computer Science, Interdisciplinary Applications
Janos Jozsef Toth, Gergo Halo, Manuel Goyanes
Summary: Previous scientometric analyses have shown that high-prestige research output tends to be concentrated in a few core countries and regions, indicating imbalances in power relations and biases within global academia. This paper investigates the geopolitical biases of impact among productive scholars in communication from 11 countries and 3 regions. The results indicate a strong US dominance in citation-based impact and reveal discrepancies in altmetric indicators between Eastern European and Spanish scholars and their American and Western European counterparts.
Article
Computer Science, Artificial Intelligence
Tao Dai, Jie Zhao, Dehong Li, Shun Tian, Xiangmo Zhao, Shirui Pan
Summary: The outbreak of COVID-19 has led to a surge in scientific literature, making it difficult for researchers, especially junior ones, to find the relevant citations for their COVID-19 research. This paper presents a novel neural network-based method called CRB-HDGCN, which effectively recommends inline citations for COVID-19 research. The method combines a citation relational BERT and a heterogeneous deep graph convolutional network to enhance the representation learning and generate accurate recommendations.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Interdisciplinary Applications
Chanathip Pornprasit, Xin Liu, Pattararat Kiattipadungkul, Natthawut Kertkeidkachorn, Kyoung-Sook Kim, Thanapon Noraset, Saeed-Ul Hassan, Suppawong Tuarob
Summary: This paper proposes a method to enhance the citation recommendation performance by capturing the global citation behavior and develops a novel citation network embedding algorithm (ConvCN) to encode the citation relationship among papers. The experimental results show that the proposed method improves the citation recommendation performance by 44.86% and 34.87% on average in terms of Bpref and F-measure@20, respectively.
Article
Information Science & Library Science
Alexander Serenko, Nick Bontis
Summary: This study updates a global ranking list of 28 knowledge management and intellectual capital academic journals, with popular journals such as Journal of Knowledge Management and Journal of Intellectual Capital ranked highly, while the newer Journal of Innovation & Knowledge has shown strong performance.
JOURNAL OF KNOWLEDGE MANAGEMENT
(2022)
Article
Computer Science, Interdisciplinary Applications
S. Ravikumar, Bidyut Bikash Boruah, M. N. Ravikumar
Summary: This study examines the correlation between citation count and Mendeley readership score for articles by Sri Lankan authors. The findings show a strong correlation between the two variables. The subject categories of 'Chemistry', 'Public, Environmental & Occupational Health', and 'Engineering' were identified as highly indexed. Articles with higher Mendeley readership scores are more likely to have higher citation counts, while articles with lower readership scores tend to have a negative correlation. Mendeley is most commonly used by researchers, Ph.D. students, and master's students.
Article
Chemistry, Multidisciplinary
Xu Yang, Ziyi Huan, Yisong Zhai, Ting Lin
Summary: This research focuses on personalized recommendation based on knowledge graphs, including constructing knowledge graphs, improving the TransE algorithm, and combining ranking learning and neural networks to build two recommendation models. Experimental results demonstrate that these models effectively enhance recommendation accuracy and recall.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Information Systems
Shikha Gupta, Naveen Kumar, Subhash Bhalla
Summary: Citation analysis evaluates the impact of scientific manuscripts, authors, and publication venues. Metrics like Impact Factor (IF) and H-index are commonly used for measuring journal and conference impact. This review categorizes citation metrics based on their applicability for evaluating journals and conferences, and discusses the role of prestige measuring indicators like SCImago Journal Rank (SJR) and Eigenfactor. The proposed Normalized Immediacy Index (IInorm) offers a way to measure the immediate relevance of articles published in journals/conferences and shows strong correlations with traditional metrics.
JOURNAL OF INFORMATION SCIENCE
(2023)
Article
Computer Science, Interdisciplinary Applications
Muhammad Salman, Mohammad Masroor Ahmed, Muhammad Tanvir Afzal
Summary: The study found that different multi-authorship indices have varying levels of correlation in ranking authors, with some showing strong correlation, weak correlation, and even negative correlation. In the top 10% rankings, the g(f)-index successfully brought in most of the award winners, but none of the indices were able to include all of the awardees in the list of top ranked authors.
Article
Physics, Multidisciplinary
Shihu Liu, Haiyan Gao
Summary: Due to its wide application across many disciplines, an efficient ranking method for nodes in graph data has become an urgent topic. Most classical methods only consider the local structure information of nodes and ignore the global structure information. This paper proposes a structure entropy-based method to rank node importance by considering both local and global structure information. Experimental results on eight real-world datasets demonstrate the effectiveness of the proposed method.
Article
Computer Science, Information Systems
Ying Kang, Aiqin Hou, Zimin Zhao, Daguang Gan
Summary: This paper explored paper recommendation methods in public digital libraries and proposed a hybrid recommendation model that combines citations and content to achieve more accurate recommendations. By using a graphical form of citation relations and the concept of citation similarity, the proposed hybrid method outperforms state-of-the-art techniques and achieves 40% higher recommendation accuracy on average compared to citation-based approaches.
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Changwon Seo, Kyeong-Joong Jeong, Sungsu Lim, Won-Yong Shin
Summary: This article presents SiReN, a new sign-aware recommender system based on GNN models. SiReN outperforms state-of-the-art NE-aided recommendation methods by constructing a signed bipartite graph, generating embeddings, and establishing a loss function.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Qingxian Wang, Suqiang Wu, Yanan Bai, Quanliang Liu, Xiaoyu Shi
Summary: The emerging topic of Graph Neural Networks (GNN) has achieved state-of-the-art performance in recommendation problems due to its strong ability in node representation. We propose BIG-SAGE@, a neighbor importance-aware GNN, for item recommendation and rating prediction. Through rating confidence-based neighborhood sampling and an attention network, BIG-SAGE@ outperforms SOTA methods in rating prediction and TopN ranking tasks.
Article
Automation & Control Systems
Jinjin Zhang, Chenhui Ma, Chengliang Zhong, Peng Zhao, Xiaodong Mu
Summary: This paper proposes a novel framework called FINI, which utilizes feature weights and interactions between neighbor nodes to improve cold start recommendation. By designing a global-local contexts attention mechanism and a mixed interaction mechanism, the expressive capability of feature embeddings and user/item embeddings are enhanced, leading to significant improvements in terms of metric evaluations.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Qianqian Xie, Yutao Zhu, Jimin Huang, Pan Du, Jian-Yun Nie
Summary: This article proposes a model called Graph Neural Collaborative Topic Model which combines the advantages of relational topic models and graph neural networks to capture high-order citation relationships and achieve higher explainability. Experimental results demonstrate that the model outperforms competitive methods in citation recommendation and is able to learn better topics.
ACM TRANSACTIONS ON INFORMATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Ghulam Mustafa, Abid Rauf, Bilal Ahmed, Muhammad Tanvir Afzal, Adnan Akhunzada, Salman Z. Alharthi
Summary: Ranking of researchers based on their scientific impact is crucial for decisions in the scientific community, and various parameters have been proposed for this purpose. However, no universally accepted parameter exists, and it is necessary to determine an optimal parameter. This research evaluates the h-index and its variants, using data from 1050 researchers in the mathematical domain and comparing correlations and rankings. The analysis reveals the importance of certain indices and a relationship between specific societies and the indices.
Article
Computer Science, Interdisciplinary Applications
Xiaorui Jiang, Chunyi Zheng, Ya Tian, Ronghua Liang
JOURNAL OF VISUALIZATION
(2015)
Article
Computer Science, Information Systems
Xiaorui Jiang, Xiaoping Sun, Zhe Yang, Hai Zhuge, Jianmin Yao
JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY
(2016)
Article
Engineering, Electrical & Electronic
Sun Guodao, Li Si, Cao Dizhou, Liu Chunhui, Jiang Xiaorui, Liang Ronghua
CHINESE JOURNAL OF ELECTRONICS
(2018)
Article
Computer Science, Artificial Intelligence
Ronghua Liang, Hai Zhuge, Xiaorui Jiang, Qiang Zeng, Xiaofei He
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2014)
Article
Computer Science, Information Systems
Xiaorui Jiang, Xinghao Zhu, Jingqiang Chen
JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY
(2020)
Article
Computer Science, Interdisciplinary Applications
Xiaorui Jiang, Hai Zhug
JOURNAL OF INFORMETRICS
(2019)
Article
Computer Science, Information Systems
Xiaorui Jiang, Junjun Liu
Summary: This paper proposes a semantic main path network analysis approach to address the issues of coherence and coverage in main path analysis by considering the semantic relationships between citing and cited publications. It builds semantic citation networks by including important citations and builds a semantic main path network by merging top-K main paths. The results show that semantic main path networks provide complementary views of scientific knowledge flows and uncover more coherent development pathways.
JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Interdisciplinary Applications
Xiaorui Jiang, Jingqiang Chen
Summary: Much effort has been devoted to citation function classification, but notable challenges remain. Limited data size and inadequate representativeness of scientific domains pose difficulties in annotation. The current state-of-the-art deep learning-based methods fail to leverage the full potential of citation modelling options. To address these issues, this paper focuses on contextualised citation function classification and proposes new models based on strong SciBERT. Additionally, a comprehensive analysis of performance and per-class analysis is conducted to evaluate the effectiveness of citation function classification for downstream applications.
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaorui Jiang, Chenhui Gao, Ronghua Liang
PROCEEDINGS OF 2016 12TH INTERNATIONAL CONFERENCE ON SEMANTICS, KNOWLEDGE AND GRIDS (SKG)
(2016)
Proceedings Paper
Computer Science, Hardware & Architecture
Xiaoping Sun, Xiangfeng Luo, Jin Liu, Xiaorui Jiang, Junsheng Zhang
2015 11TH INTERNATIONAL CONFERENCE ON SEMANTICS, KNOWLEDGE AND GRIDS (SKG)
(2015)
Proceedings Paper
Computer Science, Hardware & Architecture
Zhengjun Ye, Chenhui Gao, Xiaorui Jiang, Ronghua Liang
2015 11TH INTERNATIONAL CONFERENCE ON SEMANTICS, KNOWLEDGE AND GRIDS (SKG)
(2015)
Proceedings Paper
Computer Science, Hardware & Architecture
Xiaorui Jiang, Xiaoping Sun, Qiang Zeng, Hai Zhuge
2013 NINTH INTERNATIONAL CONFERENCE ON SEMANTICS, KNOWLEDGE AND GRIDS (SKG)
(2013)
Article
Computer Science, Information Systems
Qiang Zeng, Xiaorui Jiang, Hai Zhuge
PROCEEDINGS OF THE VLDB ENDOWMENT
(2012)