Joint Modeling of Citation Networks and User Preferences for Academic Tagging Recommender System

In the tag recommendation task on academic platforms,existing methods disregard users’customized preferences in favor of extracting tags based just on the content of the articles.Besides,it uses co-occurrence techniques and tries to combine nodes’textual content for modelling.They still do not,however,directly simulate many interactions in network learning.In order to address these issues,we present a novel system that more thoroughly integrates user preferences and citation networks into article labelling recommendations.Specifically,we first employ path similarity to quantify the degree of similarity between user labelling preferences and articles in the citation network.Then,the Commuting Matrix for massive node pair paths is used to improve computational performance.Finally,the two commonalities mentioned above are combined with the interaction paper labels based on the additivity of Poisson distribution.In addition,we also consider solving the model’s parameters by applying variational inference.Experimental results demonstrate that our suggested framework agrees and significantly outperforms the state-of-the-art baseline on two real datasets by efficiently merging the three relational data.Based on the Area Under Curve(AUC)and Mean Average Precision(MAP)analysis,the performance of the suggested task is evaluated,and it is demonstrated to have a greater solving efficiency than current techniques.

Tracking direct and indirect impact on technology and policy of transformative research via ego citation network

Purpose:The disseminating of academic knowledge to nonacademic audiences partly relies on the transition of subsequent citing papers.This study aims to investigate direct and indirect impact on technology and policy originating from transformative research based on ego citation network.Design/methodology/approach:Key Nobel Prize-winning publications(NPs)in fields of gene engineering and astrophysics are regarded as a proxy for transformative research.In this contribution,we introduce a network-structural indicator of citing patents to measure technological impact of a target article and use policy citations as a preliminary tool for policy impact.Findings:The results show that the impact on technology and policy of NPs are higher than that of their subsequent citation generations in gene engineering but not in astrophysics.Research limitations:The selection of Nobel Prizes is not balanced and the database used in this study,Dimensions,suffers from incompleteness and inaccuracy of citation links.Practical implications:Our findings provide useful clues to better understand the characteristics of transformative research in technological and policy impact.Originality/value:This study proposes a new framework to explore the direct and indirect impact on technology and policy originating from transformative research.

Discovering the communication structures of directed weighted citation networks in library and information science through Pathfinder

Communication structures mining is of importance for the understanding of the communities of a domain and knowledge flow among papers and authors.In this paper,we take advantage of Pathfinder,a method for pruning networks,to discover the communities of a directed weighted citation network and its main knowledge flow structure.Meanwhile,in the course of the analysis,necessary data transformations are carried out,and proper parameters for Pathfinder are determined.It is found that Pathfinder plays a multifaceted role in the discovery of communication structures of directed weighted citation networks,which could provide more systematic insights to citation network analytics.

Recommending Authors and Papers Based on ACTTM Community and Bilayer Citation Network

Citation network is often used for academic recommendation. However, it is difficult to achieve high recommendation accuracy and low time complexity because it is often very large and sparse and different citations have different purposes. What's more, some citations include unreasonable information, such as in case of intentional self-citation. To improve the accuracy of citation network-based academic recommendation and reduce the time complexity, we propose an academic recommendation method for recommending authors and papers. In which, an author-paper bilayer citation network is built, then an enhanced topic model, Author Community Topic Time Model(ACTTM) is proposed to detect high quality author communities in the author layer, and a set of attributes are proposed to comprehensively depict the author/paper nodes in the bilayer citation network. Experimental results prove that the proposed ACTTM can detect high quality author communities and facilitate low time complexity, and the proposed academic recommendation method can effectively improve the recommendation accuracy.

An author credit allocation method with improved distinguishability and robustness

Purpose:The purpose of this study is to propose an improved credit allocation method that makes the leading author of the paper more distinguishable and makes the deification more robust under malicious manipulations.Design/methodology/approach:We utilize a modified Sigmoid function to handle the fat-tail distributed citation counts.We also remove the target paper in calculating the contribution of co-citations.Following previous studies,we use 30 Nobel Prize-winning papers and their citation networks based on the American Physical Society(APS)and the Microsoft Academic Graph(MAG)dataset to test the accuracy of our proposed method(NCCAS).In addition,we use 654,148 articles published in the field of computer science from 2000 to 2009 in the MAG dataset to validate the distinguishability and robustness of NCCAS.Finding:Compared with the state-of-the-art methods,NCCAS gives the most accurate prediction of Nobel laureates.Furthermore,the leading author of the paper identified by NCCAS is more distinguishable compared with other co-authors.The results by NCCAS are also more robust to malicious manipulation.Finally,we perform ablation studies to show the contribution of different components in our methods.Research limitations:Due to limited ground truth on the true leading author of a work,the accuracy of NCCAS and other related methods can only be tested in Nobel Physics Prize-winning papers.Practical implications:NCCAS is successfully applied to a large number of publications,demonstrating its potential in analyzing the relationship between the contribution and the recognition of authors with different by-line orders.Originality/value:Compared with existing methods,NCCAS not only identifies the leading author of a paper more accurately,but also makes the deification more distinguishable and more robust,providing a new tool for related studies.

Are Contributions from Chinese Physicists Undercited?

Purpose:In this work,we want to examine whether or not there are some scientific fields to which contributions from Chinese scholars have been un der or over cited.Design/methodology/approach:We do so by comparing the number of received citations and the IOF of publications in each scientific field from each country.The IOF is calculated from applying the modified closed system input–output analysis(MCSIOA)to the citation network.MCSIOA is a PageRank-like algorithm which means here that citations from the more influential subfields are weighted more towards the IOF.Findings:About 40% of subfields in physics in China are undercited,meaning that their net influence ranks are higher(better)than the direct rank,while about 75% of subfields in the USA and German are undercited.Research limitations:Only APS data is analyzed in this work.The expected citation influence is assumed to be represented by the IOF,and this can be wrong.Practical implications:MCSIOA provides a measure of net influences and according to that measure.Overall,Chinese physicists’publications are more likely overcited rather than being undercited.Originality/value:The issue of under or over cited has been analyzed in this work using MCSIOA.

ComRank： Joint Weight Technique for the Identification of Influential Communities

Recently, the community analysis has seen enormous research advancements in the field of social networks. A large amount of the current studies put forward different models and algorithms about most influential people. However, there is little work to shed light on how to rank communities while considering their levels that are determined by the quality of their published contents. In this paper, we propose solution for measuring the influence of communities and ranking them by considering joint weight composed of internal and external influence of communities. To address this issue, we design a novel algorithm called Com Rank: a modification of Page Rank, which considers the joint weight in order to identify impact of each community and ranking them. We use real-world data trace in citation network and perform extensive experiments to evaluate our proposed algorithm. The comparative results depict significant improvements by our algorithm in community ranking due to the inclusion of proposed weighting feature.

Three decades of topic evolution,hot spot mining and prospect in CCUS Studies based on CitNetExplorer

As a major strategic technology for reducing greenhouse gas emissions and ensuring energy security,carbon capture,utilization,and storage(CCUS)is of great significance to large-scale emission reduction.From the perspective of knowledge discovery,it is important to analyse the study progress based on existing study achievements,excavate the evolution characteristics of study topics over time,review stage-specific findings,and construct CCUS domain knowledge map.This will help researchers gain an overall understanding of CCUS studies and promote the industry-college-research cooperation in respect to CCUS.Based on the Web of Science(WOS)database platform and CitNet-Explorer software,the present study explore the international research progress,topic evolution track,research hotspot and research trend of CCUS technology since its birth nearly 30 years ago,using bibliometric method,citation network visualization analysis method and cluster analysis method.Through the analysis of literature citation network,it is found that:16 CCUS topics,6 hotspots have been studied in the last three decades.The topics of CCUS studies present an evolution path from CCUS technology security and economicfeasibility analysis to CCUS technological popularization,and then CCUS technological improvement and development.Cutting-edge CCUS looks at the process and infrastructure construction,cost effectiveness and development prospect analysis.CCUS focuses on improvement of process technologies and related infrastructure.

Traversing knowledge networks:an algorithmic historiography of extant literature on the Internet of Things(IoT)

Research on the Internet of Things(IoT)has been booming for the past 6 years due to technological advances and potential for application.Nonetheless,the rapid growth of IoT articles and the heterogeneous nature of IoT pose challenges to conducting a systematic review of IoT literature.This study seeks to address the abovementioned challenges by reviewing 1065 IoT articles retrieved from the International Statistical Institute Web of Science via a blend of quantitative citation analysis and qualitative content analysis.For the former,we generated a historiography of IoT research,a citation network,in which we tried to identify main paths of codification and diffusion,as well as path-dependent transitions.For the latter,we explicated the progression of knowledge through 30 central IoT articles in chronological order regarding infrastructures,enabling technologies,potential technologies,and research challenges.Findings from this study contribute to both IoT research and management.

A citation iteration method for publications and scientists evaluation

In the last decades many methods have been developed for the evaluation of the quality and impact of both the scientific research papers and scientists.Effectively identifying,discovering,and evaluating high-impact papers using scientometric methods,and adopting reasonable evaluation procedures and methods are vital to stimulating scientists’creative vitality.Examples of methods used for evaluating impact are:h-index and the cited frequency of articles and the number of highly cited papers.Here we propose a new method to assess the scientist impact based on citation iteration.The method was inspired in the Page Rank algorithm.In the present study,both the number of citations and the citing publications after each citation were considered.According to the obtained results,the proposal allows a more accurate measurement of the impact of scientific papers.Also,the application of this method,it can greatly improve the judgment efficiency of high-impact scientists.We have also conducted an empirical study at three levels in the discipline of mathematics,namely the comparisons of two publications,two scientists and eight scientists.Results show that indexes proposed in this dissertation designed for the publications’impacts evaluation and scientists’impact evaluation can be used to find the cause behind the number of cited frequencies resulting in the impact difference.The Q-index for publications’impacts evaluation and F-index for scientists’impacts evaluation proposed in this article can be used more accurately to check and evaluate the impact of scientists.Additionally,these new indexes can be used in the research management of departments at all levels,and can be useful by the states to find leading scientists in several fields.

Hybrid scientific article recommendation system with COOT optimization

Today, recommendation systems are everywhere, making a variety of activities considerably more manageable. These systems help users by personalizing their suggestions to their interests and needs. They can propose various goods, including music, courses, articles, agricultural products, fertilizers, books, movies, and foods. In the case of research articles, recommendation algorithms play an essential role in minimizing the time required for researchers to find relevant articles. Despite multiple challenges, these systems must solve serious issues such as the cold-start problem, article privacy, and changing user interests. This research addresses these issues through the use of two techniques: hybrid recommendation systems and COOT optimization. To generate article recommendations, a hybrid recommendation system integrates features from content-based and graph-based recommendation systems. COOT optimization is used to optimize the results, inspired by the movement of water birds. The proposed method combines a graph-based recommendation system with COOT optimization to increase accuracy and reduce result inaccuracies. When compared to the baseline approaches described, the model provided in this study improves precision by 2.3%, recall by 1.6%, and mean reciprocal rank (MRR) by 5.7%.

Research on potential influential scholars in the field of information science and their cooperative characteristics

With the continuous development of social media,the ways and means of academic influence evaluation of scholars are increasing rapidly.The emergence of the Citation Network Structural Variation model method breaks the traditional way of identifying the influence of scholars through scientometrics index,author cooperation or node indicators in author citation network structure.Based on this method,CiteSpace software tool is used to detect scholars with potential influence in the field of Information Science and reveal the cooperative characteristics of scholars with potential influence.The study found that the most potentially influential five-pointed star scholars in the field of Information Science mainly include Leydesdorff L,Bornmann L,Thelwall M,Bar-llan J,Waltman L,Huang MH,Rousseau R and others.Pentagram scholars are usually located at the core of different cooperative groups in the author's cooperative network.Other influential non-pentagram scholars and pentagram scholars maintain a high frequency of cooperation and have a high similarity in research direction.

Identifying the Key Reference of a Scientific Publication

The most fundamental way to measure the impact of a scientific publication is using the number of citations it received.Though citation count and its variants are widely adopted,they have been pointed out to be poor proxies for a paper's quality because a citation might result from different reasons.It is thus crucial to quantify the true relevance of the cited papers to the citing paper.There are already some eforts in the literature devoted to addressing this isue,yet a well-accepted method is still lacking,possibly due to the absence of standard ground truth data for comparing different methods.In this paper,we propose a simple method using a local diffusion process on citation networks for identifying the key references for each scientific publication.The effectiveness and of the method are validated in a subset of the American Physical Society data in which the key references are mentioned in the abstract of papers.We further define an effective citation metric for quantifying the actual impact of each paper and its evolution.The effective citation metric additionally reveals the citation preference of research at journal and country levels.