Findme-scholar：一个上下文研究者推荐系统，用于使用自适应主题兴趣领域建模来加强研究合作

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX Pub Date : 2025-08-24 DOI:10.1016/j.mex.2025.103583

Ary Mazharuddin Shiddiqi , Moch. Nafkhan Alzamzami , Ilham Gurat Adillion , Mohammad Idris Arif Budiman , Ricardo Supriyanto , Muhammad Machmud

{"title":"Findme-scholar：一个上下文研究者推荐系统，用于使用自适应主题兴趣领域建模来加强研究合作","authors":"Ary Mazharuddin Shiddiqi , Moch. Nafkhan Alzamzami , Ilham Gurat Adillion , Mohammad Idris Arif Budiman , Ricardo Supriyanto , Muhammad Machmud","doi":"10.1016/j.mex.2025.103583","DOIUrl":null,"url":null,"abstract":"<div><div>Identifying potential research collaborators with aligned expertise and complementary interests remains a persistent challenge, particularly in multidisciplinary and large-scale academic environments. This paper introduces Findme-Scholar, a contextual researcher recommender system aimed at enhancing research collaboration through adaptive topic interest area modelling. The system dynamically captures researchers' evolving thematic interests by analyzing publication metadata and semantic content to provide context-aware recommendations that surpass traditional static profile matching approaches. Our method successfully recommended researchers without prior co-authorship links to the target individual, demonstrating its ability to identify potential collaborators beyond existing networks. This result reflects the method’s effectiveness in capturing thematic and contextual similarities to discover relevant yet previously unconnected researchers.<ul><li><span>•</span><span><div>Findme-Scholar models evolving research interests for better collaboration.</div></span></li><li><span>•</span><span><div>Recommends collaborators beyond existing co-authorship networks.</div></span></li><li><span>•</span><span><div>Uses semantic and metadata analysis for context-aware suggestions.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103583"},"PeriodicalIF":1.9000,"publicationDate":"2025-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Findme-scholar: a contextual researcher recommender system for enhancing research collaboration using adaptive topic interest area modelling\",\"authors\":\"Ary Mazharuddin Shiddiqi , Moch. Nafkhan Alzamzami , Ilham Gurat Adillion , Mohammad Idris Arif Budiman , Ricardo Supriyanto , Muhammad Machmud\",\"doi\":\"10.1016/j.mex.2025.103583\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Identifying potential research collaborators with aligned expertise and complementary interests remains a persistent challenge, particularly in multidisciplinary and large-scale academic environments. This paper introduces Findme-Scholar, a contextual researcher recommender system aimed at enhancing research collaboration through adaptive topic interest area modelling. The system dynamically captures researchers' evolving thematic interests by analyzing publication metadata and semantic content to provide context-aware recommendations that surpass traditional static profile matching approaches. Our method successfully recommended researchers without prior co-authorship links to the target individual, demonstrating its ability to identify potential collaborators beyond existing networks. This result reflects the method’s effectiveness in capturing thematic and contextual similarities to discover relevant yet previously unconnected researchers.<ul><li><span>•</span><span><div>Findme-Scholar models evolving research interests for better collaboration.</div></span></li><li><span>•</span><span><div>Recommends collaborators beyond existing co-authorship networks.</div></span></li><li><span>•</span><span><div>Uses semantic and metadata analysis for context-aware suggestions.</div></span></li></ul></div></div>\",\"PeriodicalId\":18446,\"journal\":{\"name\":\"MethodsX\",\"volume\":\"15 \",\"pages\":\"Article 103583\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2025-08-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"MethodsX\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2215016125004273\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MULTIDISCIPLINARY SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"MethodsX","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2215016125004273","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}

引用次数: 0

摘要

确定具有一致专业知识和互补兴趣的潜在研究合作者仍然是一个持续的挑战，特别是在多学科和大规模的学术环境中。本文介绍了Findme-Scholar，一个情境研究者推荐系统，旨在通过自适应主题兴趣领域建模来加强研究合作。该系统通过分析出版物元数据和语义内容来动态捕获研究人员不断发展的主题兴趣，从而提供超越传统静态概要匹配方法的上下文感知推荐。我们的方法成功地推荐了与目标个体没有合作关系的研究人员，证明了它在现有网络之外识别潜在合作者的能力。这一结果反映了该方法在捕捉主题和上下文相似性以发现相关但以前未连接的研究人员方面的有效性。•Findme-Scholar对不断发展的研究兴趣进行建模，以实现更好的合作。•推荐现有合作伙伴网络之外的合作者。•使用语义和元数据分析上下文感知的建议。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Findme-scholar: a contextual researcher recommender system for enhancing research collaboration using adaptive topic interest area modelling

查看原文本刊更多论文

Findme-scholar: a contextual researcher recommender system for enhancing research collaboration using adaptive topic interest area modelling

Identifying potential research collaborators with aligned expertise and complementary interests remains a persistent challenge, particularly in multidisciplinary and large-scale academic environments. This paper introduces Findme-Scholar, a contextual researcher recommender system aimed at enhancing research collaboration through adaptive topic interest area modelling. The system dynamically captures researchers' evolving thematic interests by analyzing publication metadata and semantic content to provide context-aware recommendations that surpass traditional static profile matching approaches. Our method successfully recommended researchers without prior co-authorship links to the target individual, demonstrating its ability to identify potential collaborators beyond existing networks. This result reflects the method’s effectiveness in capturing thematic and contextual similarities to discover relevant yet previously unconnected researchers.