{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:06:49Z","timestamp":1776974809205,"version":"3.51.4"},"reference-count":20,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T00:00:00Z","timestamp":1736121600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,2,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>In this paper, we develop a heterogeneous graph network using citation relations between papers and their basic information centered around the \u201cPaper mills\u201d papers under withdrawal observation, and we train graph neural network models and classifiers on these heterogeneous graphs to classify paper nodes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design\/methodology\/approach<\/jats:title>\n                    <jats:p>Our proposed citation network-based \u201cPaper mills\u201d detection model (PDCN model for short) integrates textual features extracted from the paper titles using the BERT model with structural features obtained from analyzing the heterogeneous graph through the heterogeneous graph attention network model. Subsequently, these features are classified using LGBM classifiers to identify \u201cPaper mills\u201d papers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>On our custom dataset, the PDCN model achieves an accuracy of 81.85% and an F1-score of 80.49% in the \u201cPaper mills\u201d detection task, representing a significant improvement in performance compared to several baseline models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Research limitations<\/jats:title>\n                    <jats:p>We considered only the title of the article as a text feature and did not obtain features for the entire article.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Practical implications<\/jats:title>\n                    <jats:p>The PDCN model we developed can effectively identify \u201cPaper mills\u201d papers and is suitable for the automated detection of \u201cPaper mills\u201d during the review process.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Originality\/value<\/jats:title>\n                    <jats:p>We incorporated both text and citation detection into the \u201cPaper mills\u201d identification process. Additionally, the PDCN model offers a basis for judgment and scientific guidance in recognizing \u201cPaper mills\u201d papers.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2478\/jdis-2025-0003","type":"journal-article","created":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T08:57:18Z","timestamp":1736153838000},"page":"167-187","source":"Crossref","is-referenced-by-count":4,"title":["A paper mill detection model based on citation manipulation paradigm"],"prefix":"10.2478","volume":"10","author":[{"given":"Jun","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science (National Model Software School), Beijing University of Posts and Telecommunications , Beijing , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Wanfang Data Co., Ltd . Beijing , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haihong","family":"E","sequence":"additional","affiliation":[{"name":"School of Computer Science (National Model Software School), Beijing University of Posts and Telecommunications , Beijing , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science (National Model Software School), Beijing University of Posts and Telecommunications , Beijing , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Qiao","sequence":"additional","affiliation":[{"name":"Beijing Wanfang Data Co., Ltd . Beijing , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"ZiChen","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science (National Model Software School), Beijing University of Posts and Telecommunications , Beijing , China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"374","published-online":{"date-parts":[[2025,1,6]]},"reference":[{"key":"2026020518350345354_j_jdis-2025-0003_ref_001","doi-asserted-by":"crossref","unstructured":"Candal-Pedreira, C., Ross, J. S., Ruano-Ravina, A., Egilman, D. S., Fern\u00e1ndez, E., & P\u00e9rez-R\u00edos, M. (2022). Retracted papers originating from Paper mills: cross sectional study. bmj, 379.","DOI":"10.1136\/bmj-2022-071517"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_002","doi-asserted-by":"crossref","unstructured":"Chakraborty, J., Pradhan, D. K., & Nandi, S. (2021). On the identification and analysis of citation pattern irregularities among journals. Expert Systems, 38(4), e12561.","DOI":"10.1111\/exsy.12561"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_003","doi-asserted-by":"crossref","unstructured":"Chen, J., Hou, H., Gao, J., Ji, Y., & Bai, T. (2019). RGCN: recurrent graph convolutional networks for targetdependent sentiment analysis. In International Conference on Knowledge Science, Engineering and Management (pp. 667-675). Cham: Springer International Publishing.","DOI":"10.1007\/978-3-030-29551-6_59"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_004","doi-asserted-by":"crossref","unstructured":"Christopher, J. (2021). The raw truth about Paper mills. FEBS letters, 595(13), 1751-1757.","DOI":"10.1002\/1873-3468.14143"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_005","doi-asserted-by":"crossref","unstructured":"da Silva, J. A. T., & Nazarovets, S. (2023). Assessment of retracted papers, and their retraction notices, from a cancer journal associated with \u201cPaper mills\u201d. Journal of Data and Information Science, 8(2), 118-125.","DOI":"10.2478\/jdis-2023-0009"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_006","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805."},{"key":"2026020518350345354_j_jdis-2025-0003_ref_007","doi-asserted-by":"crossref","unstructured":"Else, H., & Van Noorden, R. (2021). The fight against fake-paper factories that churn out sham science. Nature, 591(7851), 516-520.","DOI":"10.1038\/d41586-021-00733-5"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_008","doi-asserted-by":"crossref","unstructured":"Else, H. (2022). \u2018Papermill alarm\u2019software flags potentially fake papers.","DOI":"10.1038\/d41586-022-02997-x"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_009","doi-asserted-by":"crossref","unstructured":"Hu, Z., Dong, Y., Wang, K., & Sun, Y. (2020). Heterogeneous graph transformer. In Proceedings of the web conference 2020 (pp. 2704-2710).","DOI":"10.1145\/3366423.3380027"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_010","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., \u2026 & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30."},{"key":"2026020518350345354_j_jdis-2025-0003_ref_011","unstructured":"Liu, Q., Barhoumi, A., & Labb\u00e9, C. (2024). Miscitations in scientific papers: dataset and detection."},{"key":"2026020518350345354_j_jdis-2025-0003_ref_012","unstructured":"Oransky, I. (2022). Nearing 5,000 retractions: A review of 2022. Retraction Watch. https:\/\/retractionwatch. com\/2022\/12\/27\/nearing-5000-retractions-a-review-of-2022\/"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_013","unstructured":"Rogerson, A. M. (2014). Detecting the work of essay mills and file swapping sites: some clues they leave behind."},{"key":"2026020518350345354_j_jdis-2025-0003_ref_014","doi-asserted-by":"crossref","unstructured":"Seifert, R. (2021). How Naunyn-Schmiedeberg\u2019s Archives of Pharmacology deals with fraudulent papers from Paper mills. Naunyn-schmiedeberg\u2019s Archives of Pharmacology, 394, 431-436.","DOI":"10.1007\/s00210-021-02056-8"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_015","doi-asserted-by":"crossref","unstructured":"Van Noorden, R. (2023). How big is science\u2019s fake-paper problem?. Nature, 623(7987), 466-467.","DOI":"10.1038\/d41586-023-03464-x"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_016","doi-asserted-by":"crossref","unstructured":"Wang, X., Ji, H., Shi, C., Wang, B., Ye, Y., Cui, P., & Yu, P. S. (2019). Heterogeneous graph attention network. In The world wide web conference (pp. 2022-2032).","DOI":"10.1145\/3308558.3313562"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_017","doi-asserted-by":"crossref","unstructured":"Wang, K., Shen, W., Yang, Y., Quan, X., & Wang, R. (2020). Relational graph attention network for aspect-based sentiment analysis. arXiv preprint arXiv:2004.12362.","DOI":"10.18653\/v1\/2020.acl-main.295"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_018","doi-asserted-by":"crossref","unstructured":"Wittau, J., Celik, S., Kacprowski, T., Deserno, T. M., & Seifert, R. (2024). Fake paper identification in the pool of withdrawn and rejected manuscripts submitted to Naunyn\u2013Schmiedeberg\u2019s Archives of Pharmacology. Naunynschmiedeberg\u2019s Archives of Pharmacology, 397(4), 2171-2181.","DOI":"10.1007\/s00210-023-02741-w"},{"key":"2026020518350345354_j_jdis-2025-0003_ref_019","unstructured":"Xu, K., Hu, W., Leskovec, J., & Jegelka, S. (2018). How powerful are graph neural networks?. arXiv preprint arXiv:1810.00826."},{"key":"2026020518350345354_j_jdis-2025-0003_ref_020","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Jin, R., & Zhou, Z. H. (2010). Understanding bag-of-words model: a statistical framework. International journal of machine learning and cybernetics, 1, 43-52.","DOI":"10.1007\/s13042-010-0001-0"}],"container-title":["Journal of Data and Information Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.2478\/jdis-2025-0003\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.2478\/jdis-2025-0003\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T18:35:41Z","timestamp":1770316541000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.2478\/jdis-2025-0003\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,6]]},"references-count":20,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12,20]]},"published-print":{"date-parts":[[2025,2,1]]}},"alternative-id":["10.2478\/jdis-2025-0003"],"URL":"https:\/\/doi.org\/10.2478\/jdis-2025-0003","relation":{},"ISSN":["2543-683X"],"issn-type":[{"value":"2543-683X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,6]]}}}