AC-Rec:基于多维特征的科研合作者推荐方法

摘要/Abstract

摘要： 社交网络平台科研工作者数量的急剧增多使得寻找与自己兴趣相近的科研合作者变得十分困难。本文提出一种在ResearchGate平台下基于多维特征的科研合作者推荐方法。该方法结合科研工作者之间论文的文本相似度、社交关联度和自身活跃度3个维度来度量关联关系，并利用多层感知机构建推荐模型进行Top-N推荐。其中文本相似度利用Doc2Vec文本深度表示模型来计算，社交关联度利用基于图的随机游走算法来计算。实验结果显示AC-Rec优于已有的基于ResearchGate的科研合作者推荐方法，当N为30时命中率达到53.90%，能够有效地推荐潜在的科研合作者。

关键词: ResearchGate, 推荐, 多层感知机, 文本相似度, 社交关联度

Abstract: The rapid increase in the number of researchers on social network platform makes it very difficult to find academic collaborators with similar interests. This paper proposes a recommendation method for academic collaborators based on multi-features under ResearchGate platform. This method combines the three features of paper text similarity, social relevance and self-activity to measure the relationship, and uses the multi-layer perception mechanism to build a recommendation model for top-N recommendation. The text similarity is calculated by the Doc2Vec text depth representation model, and the social relevance is calculated by graph-based random walk algorithm. The experimental results show that AC-Rec is better than the existing academic collaborators recommendation methods based on ResearchGate platform. When N is 30, the hit rate reaches 53.90%, which can effectively recommend potential academic collaborators.

Key words: ResearchGate, recommendation, multi-layer perceptron, text similarity, social relevance

邵孟巧, 吉顺慧, 张鹏程. AC-Rec:基于多维特征的科研合作者推荐方法[J]. 计算机与现代化, 2021, 0(03): 94-100.

SHAO Meng-qiao, JI Shun-hui, ZHANG Peng-cheng. AC-Rec: Academic Collaborators Recommendation Method Based on Multi-features[J]. Computer and Modernization, 2021, 0(03): 94-100.

参考文献

［1］ RODRIGUES M W, BRANDAO W C, ZARATE L E. Recommending scientific collaboration from ResearchGate［C］// 2018 7th Brazilian Conference on Intelligent Systems. 2018:336-341.
［2］ XIA F, CHEN Z, WANG W, et al. MVCWalker: Random walk-based most valuable collaborators recommendation exploiting academic factors［J］. IEEE Transactions on Emerging Topics in Computing, 2014,2（3）:364-375.
［3］ MOREIRA C, CALADO P, MARTINS B. Learning to rank academic experts in the dblp dataset［J］. Expert Systems, 2015,32（4）:477-493.
［4］ KONG X J, JIANG H Z, YANG Z, et al. Exploiting publication contents and collaboration networks for collaborator recommendation［J］. PLoS One, 2016,11（2）:1-13.
［5］ SURIAN D, LIU N, LO D, et al. Recommending people in developers collaboration network［C］// Working Conference on Reverse Engineering. 2011:379-388.
［6］ LAPPAS T, LIU K, TERZI E. Finding a team of experts in social networks［C］// Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2009:467-476.
［7］ CANFORA G, PENTA M D, OLIVETO R, et al. Who is going to mentor newcomers in open source projects?［C］// Proceedings of the ACM SIGSOFT 20th International Symposium on the Foundations of Software Engineering. 2012:1-11.
［8］ DU G Y, LIU Y C, YU J J. Scientific users interest detection and collaborators recommendation［C］// International Conference on Big Data. 2018:72-79.
［9］ THELWALL M, KOUSHA K.ResearchGate: Disseminating, communicating, and measuring scholarship?［J］. Journal of the Association for Information Science and Technology, 2015,66（5）:876-889.
［10］ DAFONTEGOMEZ A, MIGUEZGONZALEZ M I, PUENTESRIVERA I. Academic social networks: Presence and activity in Academia.edu and ResearchGate of communication researchers of the Galician universities［C］// Iberian Conference on Information Systems and Technologies. 2015:1-6.
［11］ MUSCANELL N, UTZ S. Social networking for scientists: An analysis on how and why academics use ResearchGate［J］. Online Information Review, 2017,41（5）:744-759.
［12］ DENG S L, TONG J J, LIN Y Q, et al. Motivating scholars responses in academic social networking sites: An empirical study on ResearchGate Q&A behavior［J］. Information Processing & Management, 2019,56（6）:1-13.
［13］ LI L, HE D Q, JENG W, et al. Answer quality characteristics and prediction on an academic Q&A site: A case study on ResearchGate［C］// Proceedings of the 24th International Conference on World Wide Web. 2015:1453-1458.
［14］曾庆旺. 基于ResearchGate的科研合作者推荐研究与实现［D］. 北京:北京交通大学, 2018.
［15］ LE Q, MIKOLOV T. Distributed representations of sentences and documents［C］// International Conference on Machine Learning. 2014:1188-1196.

［16］ MIKOLOV T, SUTSKEVER I, CHEN KAI, et al. Distributed representations of words and phrases and their compositionality［C］// Advances in Neural Information Processing Systems. 2013:3111-3119.

［17］苏东出. 基于TF-IDF和余弦相似度的图书馆OPAC系统的研究和实现［J］. 内蒙古科技与经济, 2019（21）:67-69.
［18］ TONG H G, FALOUTSOS C, PAN J Y. Fast random walk with restart and its applications［C］// International Conference on Data Mining. 2006:613-622.
［19］ LATAPY M, PONS P. Computing communities in large networks using random walks［J］. Journal of Graph Algorithms and Applications, 2006,10（2）:191-218.
［20］项亮. 推荐系统实践［M］. 北京:人民邮电出版社, 2012.
［21］ ZHANG P C, JIA Y Y, GAO J, et al. Short-term rainfall forecasting using multi-layer perceptron［J］. IEEE Transactions on Big Data, 2020,6（1）:93-106.
［22］ RUCK D W, ROGERS S K, KABRISKY M. Feature selection using a multilayer perceptron［J］. Journal of Neural Network Computing, 1990,2（2）:40-48.
［23］ ZHANG S A, YAO L, SUN A X, et al. Deep learning based recommender system: A survey and new perspectives［J］. ACM Computing Surveys, 2018,1（1）:1-35.
［24］张鹏程,贾旸旸. 一种基于多层感知器的动态区域联合短时降水预报方法［J］. 计算机应用与软件, 2018,35（11）:159-164.
［25］周志华. 机器学习［M］. 北京:清华大学出版社, 2016.
［26］ LAU J H, BALDWIN T. An empirical evaluation of Doc2Vec with practical insights into document embedding generation［J］.Computation and Language, 2016:arXiv:1607.05368.
［27］ LIAW A, WIENER M. Classification and regression with random forest［J］. R News, 2002,23（23）:18-22.
［28］ LEE S L. Commodity recommendations of retail business based ondecisiontree induction［J］. Expert Systems with Applications, 2010,37（5）:3685-3694.
［29］ YU H, XIE T T, PASZCZYNSKI S, et al. Advantages of radial basis function networks for dynamic system design［J］. IEEE Transactions on Industrial Electronics, 2011,58（12）:5438-5450.
［30］ ZHAO C Y, ZHANG H X, ZHANG X Y, et al. Application of support vector machine （SVM） for prediction toxic activity of different data sets［J］. Toxicology, 2006,217（2-3）:105-119.

[1]	何思达, 陈平华. 基于意图的轻量级自注意力序列推荐模型[J]. 计算机与现代化, 2024, 0(12): 1-9.
[2]	焦一凯1, 2, 朱欣娟1, 2. 公共文化资源标签推荐方法[J]. 计算机与现代化, 2024, 0(10): 107-112.
[3]	于天一, 李剑锋, 陈海龙, 翟军. 隐性角色下的协同推荐算法[J]. 计算机与现代化, 2024, 0(09): 1-7.
[4]	刘彧轩1, 2, 廖宇晨1, 刘忠慧1. 单条件三元概念构建及其融合推荐应用[J]. 计算机与现代化, 2024, 0(07): 1-6.
[5]	刘雨萌, 訾玲玲, 丛鑫. 基于元路径和注意力机制特征融合的知识概念推荐[J]. 计算机与现代化, 2024, 0(05): 38-45.
[6]	翟梅. 个性化新闻推荐系统研究综述及探讨[J]. 计算机与现代化, 2024, 0(04): 12-20.
[7]	杨孟, 杨进, 陈步前. 基于知识图谱的多目标可解释性推荐[J]. 计算机与现代化, 2024, 0(03): 34-40.
[8]	王晓霞, 孟佳娜, 江烽, 丁梓晴. 基于多视图的知识感知推荐系统#br#[J]. 计算机与现代化, 2024, 0(02): 100-107.
[9]	苏欣. 数据驱动的焊膏印刷工艺参数推荐技术[J]. 计算机与现代化, 2024, 0(01): 99-102.
[10]	林威. 基于自监督学习和数据回放的新闻推荐模型增量学习方法[J]. 计算机与现代化, 2023, 0(12): 1-6.
[11]	刘语珵, 贺奇, 董延华, 王晓宇. 结合时间相关度与课程搭配度的课程推荐方法[J]. 计算机与现代化, 2023, 0(12): 53-58.
[12]	王宇航, 董宝良, 公超, 尚真真, 姚康宁. 基于意图识别的空中群目标动态威胁评估[J]. 计算机与现代化, 2023, 0(12): 100-104.
[13]	朱宏启, 王诚. 基于电商用户行为的隐式反馈推荐应用研究[J]. 计算机与现代化, 2023, 0(11): 44-50.
[14]	郑海利, 陈平华. 基于动态卷积和自注意力的序列推荐模型[J]. 计算机与现代化, 2023, 0(10): 9-16.
[15]	杨柳青, 王冲. 基于极大熵的Web服务资源个性化推荐方法[J]. 计算机与现代化, 2023, 0(09): 32-37.