Learning multi-resolution representations of research patterns in bibliographic networks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, O.-J. | - |
dc.contributor.author | Jeon, H.-J. | - |
dc.contributor.author | Jung, J.J. | - |
dc.date.accessioned | 2021-05-20T08:40:28Z | - |
dc.date.available | 2021-05-20T08:40:28Z | - |
dc.date.issued | 2021-02 | - |
dc.identifier.issn | 1751-1577 | - |
dc.identifier.issn | 1875-5879 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/44030 | - |
dc.description.abstract | This study aims at representing research patterns of bibliographic entities (e.g., scholars, papers, and venues) with a fixed-length vector. Bibliographic network structures rooted in the entities are incredibly diverse, and this diversity increases in the outstanding entities. Thus, despite their significant volume, the outstanding entities obtain minimal learning opportunities, whereas low-performance entities are over-represented. This study solves the problem by representing the patterns of the entities rather than depicting individual entities in a precise manner. First, we describe structures rooted in the entities using the Weisfeiler-Lehman (WL) relabeling process. Each subgraph generated by the relabeling process provides information on the scholars, kinds of papers they published, standards of venues in which the papers were published, and types of their collaborators. We assume that a subgraph depicts the research patterns of bibliographic entities, such as the preference of a scholar in choosing either a few highly impactful papers or numerous papers of moderate impact. Then, we simplify the subgraphs according to multiple levels of detailedness. Original subgraphs represent the individuality of the entities, and simplified subgraphs represent the entities sharing the same research patterns. In addition, simplified subgraphs balance the learning opportunities of high- and low-performance entities by co-occurring with both types of entities. We embed the subgraphs using the Skip-Gram method. If the results of the embedding represent the research patterns of the entities, the obtained vectors should be able to represent various aspects of the research performance in both the short-term and long-term durations regardless of the performances of the entities. Therefore, we conducted experiments for predicting 23 performance indicators during four time periods for four performance groups (top 1%, 5%, 10%, and all entities) using only the vector representations. The proposed model outperformed the existing network embedding methods in terms of both accuracy and variance. © 2020 Elsevier Ltd. | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Elsevier Ltd | - |
dc.title | Learning multi-resolution representations of research patterns in bibliographic networks | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.joi.2020.101126 | - |
dc.identifier.bibliographicCitation | Journal of Informetrics, v.15, no.1 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.wosid | 000632614000003 | - |
dc.identifier.scopusid | 2-s2.0-85099880567 | - |
dc.citation.number | 1 | - |
dc.citation.title | Journal of Informetrics | - |
dc.citation.volume | 15 | - |
dc.type.docType | Article | - |
dc.publisher.location | 네델란드 | - |
dc.subject.keywordAuthor | Bibliographic network embedding | - |
dc.subject.keywordAuthor | Level-wise simplification | - |
dc.subject.keywordAuthor | Multi-resolution representation learning | - |
dc.subject.keywordAuthor | Outstanding scholars | - |
dc.subject.keywordAuthor | Skewed distribution | - |
dc.subject.keywordPlus | Bibliographies | - |
dc.subject.keywordPlus | Embeddings | - |
dc.subject.keywordPlus | Learning opportunity | - |
dc.subject.keywordPlus | Multi resolution representation | - |
dc.subject.keywordPlus | Network embedding | - |
dc.subject.keywordPlus | Network structures | - |
dc.subject.keywordPlus | Performance group | - |
dc.subject.keywordPlus | Performance indicators | - |
dc.subject.keywordPlus | Research performance | - |
dc.subject.keywordPlus | Vector representations | - |
dc.subject.keywordPlus | Paper | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Information Science & Library Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Interdisciplinary Applications | - |
dc.relation.journalWebOfScienceCategory | Information Science & Library Science | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | ssci | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.