计算机科学 ›› 2020, Vol. 47 ›› Issue (12): 106-113.doi: 10.11896/jsjkx.200300107
所属专题： 复杂系统的软件工程和需求工程
余敦辉1,2, 成涛1, 袁旭1
YU Dun-hui1,2, CHENG Tao1, YUAN Xu1
摘要： 为了更有效地实现软件众包任务推荐提升软件开发质量为工人推荐合适的任务降低工人利益受损风险以达到工人和众包平台双赢的效果设计了一种基于排序学习的软件众包任务推荐方法.首先基于改进的隐语义模型提取工人-任务间的隐含特征;然后结合隐式信息对排序学习模型进行改进并将提取的隐含特征进行排序学习训练获得最优排序模型;最终通过排序模型对测试集任务进行排序得到任务推荐列表从而为工人进行众包任务推荐并采用NDCGMAPRecall推荐评价指标对推荐结果进行检验.实验表明所设计的方法能有效提高软件众包任务推荐的精度其推荐评价指标的NDCGMAPRecall值分别达到0.7220.3260.169.与基于用户的协同过滤算法相比推荐精度提升了18.6%;与仅基于RankNet的排序学习算法相比精度提升了10.2%因此能够有效指导软件众包任务推荐.
中图分类号:
| [1] STOL K J,LATOZA T D,BIRD C.Crowdsourcing for Soft-ware Engineering[J].IEEE Software,2017,34(2):30-36. [2] KE M,LICIA C,MARK H,et al.A survey of the use ofcrowdsourcing in software engineering[J].The Journal of Systems &Software,2017:57-84. [3] KARIM M R,YANG Y,MESSINGER D,et al.Learn orEarn?-Intelligent Task Recommendation for Competitive Crowdsourced Software Development[C]//Hawaii International Conference on System Sciences.2018. [4] AMBATI V,VOGEL S,CARBONELL J.Towards task recommendationin micro-task markets[C]//Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence.2011:80-83. [5] YUEN M C,KING I,LEUNG K S.Taskrec:probabilistic matrix factorization in task recommendation in crowdsourcing systems[C]//International Conference on Neural Information Processing.Springer,Berlin,Heidelberg,2012:516-525. [6] LIU M B,MAN J F,PENG C,et al.Multidimensional recommendation algorithm with implicit feedback[J].Application Research of Computers,2020,37(1):158-162. [7] ZHU J,SHEN B,HU F.A learning to rank framework for developer recommendation in software crowdsourcing[C]//2015 Asia-Pacific Software Engineering Conference (APSEC).IEEE,2015:285-292. [8] FU Y,CHEN H,SONG F.STWM:A solution to self-adaptive task-worker matching in software crowdsourcing[C]//International Conference on Algorithms and Architectures for Parallel Processing.Springer,Cham,2015:383-398. [9] LI N,MO W,SHEN B.Task recommendation with developersocial network in software crowdsourcing[C]//2016 23rd Asia-Pacific Software Engineering Conference (APSEC).IEEE,2016:9-16. [10] ZHONG Q Y,ZHANG Y,LI C,et al.Task recommendationmethod based on workers' interest and competency for crowdsourcing[J].Systems Engineering Theory &Practice,2017,37(12):3270-3280. [11] MAO K,YANG Y,WANG Q,et al.Developer recommendation for crowdsourced software development tasks[C]//2015 IEEE Symposium on Service-Oriented System Engineering.IEEE,2015:347-356. [12] SHAO W,WANG X,JIAO W.A developer recommendationframework in software crowdsourcing development[C]//National Software Application Conference.Springer,Singapore,2016:151-164. [13] AANCHAL M,NEHA J,EMILIE C,et al.Deep latent factormodel for collaborative filtering[J].Signal Processing,2019,169:107366. [14] WU K.Research on Personalized Recommendation AlgorithmBased on Latent Factor Model[D].Guangzhou:Guangdong University of Technology ,2016. [15] FAN H T,ZHONG C L,GONG H H.Latent Factor Model Based Personalized Recommendation[J].Computer Applications and Software,2017,34(12):206-210. [16] HUANG Z H,ZHANG J W,TIAN C Q,et al.Survey on Learning-to-Rank Based Recommendation Algorithms[J].Journal of Software,2016,27(3):691-713. [17] HANG L I.A short introduction to learning to rank[J].IEICE TRANSACTIONS on Information and Systems,2011,94(10):1854-1862. [18] WANG H,XU C,XU Z S.An approach to evaluate the methods of determining experts' objective weights based on evolutionary game theory[J].Knowledge-Based Systems,2019,182(15):104862.1-104862.16. [19] WU Y K,SONG R S,CHEN B.A Comprehensive WeightMethod Based on the Game Theory for Information Security Risk Assessment[J].Computer Engineering and Science,2011,33(5):9-13. [20] SONG Y,WANG H,HE X.Adapting deep RankNet for personalized search[C]//Acm International Conference on Web Search &Data Mining.ACM,2014. [21] YANG X H,LI B,HE P,et al.An Approach to Project Recommendation in Collective Software Develoment[J].Journal of Chinese Computer Systems,2015,36(4):671-676. [22] LU L,WEI D Y.A Collaborative Filtering Algorithm Based on Latent Factor Model[J].Microelectronics Computer,2015(2):73-75. |
| [1] | 张健雄, 宋坤, 何鹏, 李兵. 基于图神经网络的软件系统中关键类的识别 Identification of Key Classes in Software Systems Based on Graph Neural Networks 计算机科学, 2021, 48(12): 149-158. https://doi.org/10.11896/jsjkx.210100200 |
| [2] | 邹海涛, 郑尚, 王琦, 于化龙, 高尚. 基于牛顿法的自适应高阶评分距离推荐模型研究 Adaptive High-order Rating Distance Recommendation Model Based on Newton Optimization 计算机科学, 2020, 47(6A): 494-499. https://doi.org/10.11896/JsJkx.190900016 |
| [3] | 杨洋, 邸一得, 刘俊晖, 易超, 周维. 基于张量分解的排序学习在个性化标签推荐中的研究 Study on Learning to Rank Based on Tensor Decomposition in Personalized Tag Recommendation 计算机科学, 2020, 47(11A): 515-519. https://doi.org/10.11896/jsjkx.191100181 |
| [4] | 康雁, 卜荣景, 李浩, 杨兵, 张亚钏, 陈铁. 基于增强注意力机制的神经协同过滤 Neural Collaborative Filtering Based on Enhanced-attention Mechanism 计算机科学, 2020, 47(10): 114-120. https://doi.org/10.11896/jsjkx.190900038 |
| [5] | 胡颖, 王莹洁, 童向荣. 基于众包工人移动轨迹的任务推荐模型 Task Recommendation Model Based on Crowd Worker’s Movement Trajectory 计算机科学, 2020, 47(10): 32-40. https://doi.org/10.11896/jsjkx.200600180 |
| [6] | 王涵, 夏鸿斌. LDA模型和列表排序混合的协同过滤推荐算法 Collaborative Filtering Recommendation Algorithm Mixing LDA Model and List-wise Model 计算机科学, 2019, 46(9): 216-222. https://doi.org/10.11896/j.issn.1002-137X.2019.09.032 |
| [7] | 郭旭, 朱敬华. 基于用户向量化表示和注意力机制的深度神经网络推荐模型 Deep Neural Network Recommendation Model Based on User Vectorization Representation and Attention Mechanism 计算机科学, 2019, 46(8): 111-115. https://doi.org/10.11896/j.issn.1002-137X.2019.08.018 |
| [8] | 何瑾琳, 刘学军, 徐新艳, 毛宇佳. 融合node2vec和深度神经网络的隐式反馈推荐模型 Implicit Feedback Recommendation Model Combining Node2vec and Deep Neural Networks 计算机科学, 2019, 46(6): 41-48. https://doi.org/10.11896/j.issn.1002-137X.2019.06.005 |
| [9] | 李红梅, 刁兴春, 曹建军, 冯钦, 张磊. 面向隐式反馈的标签感知推荐方法 Tag-aware Recommendation Method with Implicit Feedback 计算机科学, 2019, 46(4): 36-43. https://doi.org/10.11896/j.issn.1002-137X.2019.04.006 |
| [10] | 王刚,王含茹,胡可,贺曦冉. 任务推荐中考虑任务关联度与时间因素的改进OCCF方法 Improved OCCF Method Considering Task Relevance and Time for Task Recommendation 计算机科学, 2018, 45(7): 172-177. https://doi.org/10.11896／j.issn.1002-137X.2018.07.030 |
| [11] | 肖迎元,张红玉. 基于用户潜在特征的社交网络好友推荐方法 Friend Recommendation Method Based on Users’ Latent Features in Social Networks 计算机科学, 2018, 45(3): 218-222. https://doi.org/10.11896/j.issn.1002-137X.2018.03.034 |
| [12] | 李铭,岳宾,代永平. 基于偏见修正的联合矩阵分解算法 Collective Matrix Factorization Algorithm Based on Bias Amendment 计算机科学, 2017, 44(Z6): 402-406. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.091 |
| [13] | 李改,陈强,李磊,潘进财. 融合社交网络的单类个性化协同排序算法 One-class Personalized Collaborative Ranking Algorithm Incorporating Social Network 计算机科学, 2017, 44(2): 88-92. https://doi.org/10.11896/j.issn.1002-137X.2017.02.011 |
| [14] | 杨潇,崔超然,王帅强. 基于矩阵分解优化的排序学习特征构造方法 Feature Construction Method for Learning to Rank Based on Optimization of Matrix Factorization 计算机科学, 2017, 44(12): 255-259. https://doi.org/10.11896/j.issn.1002-137X.2017.12.046 |
| [15] | 俞春花,刘学军,李斌. 隐式反馈场景中融合社交信息的上下文感知推荐 Implicit Feedback Personalized Recommendation Model Fusing Context-aware and Social Network Process 计算机科学, 2016, 43(6): 248-253. https://doi.org/10.11896/j.issn.1002-137X.2016.06.049 |
|
||
首页