SentenceLDA- and ConNetClus-Based Heterogeneous Academic Network Analysis for Publication Ranking
Scientific papers published in journals or conferences, also considered academic publications, are the manifestation of scientific research achievements. Lots of scientific papers published in digital form bring new challenges for academic evaluation and information retrieval. Therefore, research on...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/15/5/159 |
| _version_ | 1797502162927878144 |
|---|---|
| author | Jinsong Zhang Bao Jin Junyi Sha Yan Chen Yijin Zhang |
| author_facet | Jinsong Zhang Bao Jin Junyi Sha Yan Chen Yijin Zhang |
| author_sort | Jinsong Zhang |
| collection | DOAJ |
| description | Scientific papers published in journals or conferences, also considered academic publications, are the manifestation of scientific research achievements. Lots of scientific papers published in digital form bring new challenges for academic evaluation and information retrieval. Therefore, research on the ranking method of scientific papers is significant for the management and evaluation of academic resources. In this paper, we first identify internal and external factors for evaluating scientific papers and propose a publication ranking method based on an analysis of a heterogeneous academic network. We use four types of metadata (i.e., author, venue (journal or conference), topic, and title) as vertexes for creating the network; in there, the topics are trained by the SentenceLDA algorithm with the metadata of the abstract. We then use the Gibbs sampling method to create a heterogeneous academic network and apply the ConNetClus algorithm to calculate the probability value of publication ranking. To evaluate the significance of the method proposed in this paper, we compare the ranking results with BM25, PageRank, etc., and homogeneous networks in MAP and NDCG. As shown in our evaluation results, the performance of the method we propose in this paper is better than other baselines for ranking publications. |
| first_indexed | 2024-03-10T03:29:00Z |
| format | Article |
| id | doaj.art-1d64d6f02e354e0f98dc48b05dd129ed |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-10T03:29:00Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-1d64d6f02e354e0f98dc48b05dd129ed2023-11-23T09:45:29ZengMDPI AGAlgorithms1999-48932022-05-0115515910.3390/a15050159SentenceLDA- and ConNetClus-Based Heterogeneous Academic Network Analysis for Publication RankingJinsong Zhang0Bao Jin1Junyi Sha2Yan Chen3Yijin Zhang4School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, ChinaSchool of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, ChinaSchool of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, ChinaSchool of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, ChinaSchool of Economics and Management, Dalian Minzu University, Dalian 116650, ChinaScientific papers published in journals or conferences, also considered academic publications, are the manifestation of scientific research achievements. Lots of scientific papers published in digital form bring new challenges for academic evaluation and information retrieval. Therefore, research on the ranking method of scientific papers is significant for the management and evaluation of academic resources. In this paper, we first identify internal and external factors for evaluating scientific papers and propose a publication ranking method based on an analysis of a heterogeneous academic network. We use four types of metadata (i.e., author, venue (journal or conference), topic, and title) as vertexes for creating the network; in there, the topics are trained by the SentenceLDA algorithm with the metadata of the abstract. We then use the Gibbs sampling method to create a heterogeneous academic network and apply the ConNetClus algorithm to calculate the probability value of publication ranking. To evaluate the significance of the method proposed in this paper, we compare the ranking results with BM25, PageRank, etc., and homogeneous networks in MAP and NDCG. As shown in our evaluation results, the performance of the method we propose in this paper is better than other baselines for ranking publications.https://www.mdpi.com/1999-4893/15/5/159heterogeneous academic networkpublication rankingSentenceLDAConNetClus |
| spellingShingle | Jinsong Zhang Bao Jin Junyi Sha Yan Chen Yijin Zhang SentenceLDA- and ConNetClus-Based Heterogeneous Academic Network Analysis for Publication Ranking Algorithms heterogeneous academic network publication ranking SentenceLDA ConNetClus |
| title | SentenceLDA- and ConNetClus-Based Heterogeneous Academic Network Analysis for Publication Ranking |
| title_full | SentenceLDA- and ConNetClus-Based Heterogeneous Academic Network Analysis for Publication Ranking |
| title_fullStr | SentenceLDA- and ConNetClus-Based Heterogeneous Academic Network Analysis for Publication Ranking |
| title_full_unstemmed | SentenceLDA- and ConNetClus-Based Heterogeneous Academic Network Analysis for Publication Ranking |
| title_short | SentenceLDA- and ConNetClus-Based Heterogeneous Academic Network Analysis for Publication Ranking |
| title_sort | sentencelda and connetclus based heterogeneous academic network analysis for publication ranking |
| topic | heterogeneous academic network publication ranking SentenceLDA ConNetClus |
| url | https://www.mdpi.com/1999-4893/15/5/159 |
| work_keys_str_mv | AT jinsongzhang sentenceldaandconnetclusbasedheterogeneousacademicnetworkanalysisforpublicationranking AT baojin sentenceldaandconnetclusbasedheterogeneousacademicnetworkanalysisforpublicationranking AT junyisha sentenceldaandconnetclusbasedheterogeneousacademicnetworkanalysisforpublicationranking AT yanchen sentenceldaandconnetclusbasedheterogeneousacademicnetworkanalysisforpublicationranking AT yijinzhang sentenceldaandconnetclusbasedheterogeneousacademicnetworkanalysisforpublicationranking |