计算机科学 ›› 2023, Vol. 50 ›› Issue (10): 282-290.doi: 10.11896/jsjkx.221000133
刘庆菊, 潘庆先, 童向荣, 于嵩, 潘亚楠
LIU Qingju, PAN Qingxian, TONG Xiangrong, YU Song, PAN Yanan
摘要： 随着移动智能终端的普及,众包采集大规模感知数据变得越来越容易。众包工人的自私性使得他们想通过最少的努力获得最多的报酬,甚至互相勾结、随意提交众包数据,导致众包任务完成质量不高。文中提出了一种基于陪审团的质量控制策略,该机制解决了数据验证问题。针对降低众包质量的行为,在判断是否存在垃圾邮件员工和共谋组织后,使用社区影响力检测算法(CIDA)来检测出共谋团伙领导者及其所在组织,最后使用改进的相似性检测算法(PI-Cosine)筛查垃圾邮件员工。从这两个方面来提高众包数据质量。实验结果表明,所提方法在accuracy和F1-score衡量指标上相比Cosine相似度检测算法提高了12.3%。
中图分类号:
| [1]HOWE J.The rise of crowdsourcing[J].Wired Magazine,2006,14(6):1-4. [2]KOROVINA O,BAEZ M,CASATI F.Reliability of crowd-sourcing as a method for collecting emotions labels on pictures[J].BMC Research Notes,2019,12(1):715-715. [3]ZHANG C,ZHU L,XU C,et al.A privacy-preserving trafficmonitoring scheme via vehicular crowdsourcing[J].Sensors(Basel),2019,19(6):1274. [4]AHMED M,KARAGIORGOU S,PFOSER D,et al.A comparison and evaluation of map construction algorithms using vehicle tracking data[J].GeoInformatica,2015,19(3):601-632. [5]CIRQUEIRA D,VINíCIUS L,PINHEIRO M,et al.OpinionLabel:A Gamified Crowdsourcing System for Sentiment[C]//Anais Estendidos do XXIII Simpósio Brasileiro de Sistemas Multimídia e Web.SBC,2017:209-213. [6]HAGERER G,SZABO D,KOCH A,et al.End-to-End Annotator Bias Approximation on Crowdsourced Single-Label Sentiment Analysis[C]//Proceedings of The Fourth International Conference on Natural Language and Speech Processing(ICNLSP 2021).2021:1-10. [7]ENNAJI F Z,FAZZIKI A E,ABDALLAOUI H,et al.ACrowdsourcing Based Framework for Sentiment Analysis:A Product Reputation[J].Journal of Communications Software and Systems,2020,16(4):285-295. [8]ZHOU J,JIN X,YU L,et al.TruthTrust:Truth Inference-Based Trust Management Mechanism on a Crowdsourcing Platform[J].Sensors(Basel,Switzerland),2021,21(8):2578. [9]KHUDABUKHSH A,CARBONELL J,JANSEN P.DetectingNon-Adversarial Collusion in Crowdsourcing[C]//Proceedings of the AAAI Conference on Human Computation and Crowdsourcing.2014,2:104-111. [10]CHEN P P,SUN H L,FANG Y L,et al.Collusion-Proof Result Inference in Crowdsourcing[J].Journal of Computer Science & Technology,2018,33(2):351-365. [11]NIAZI T M,AMINTOOSI H.Collusion-resistant worker selection in social crowdsensing systems[J].Computer and Know-ledge Engineering,2018,1(1):9-20. [12]AKKERHUIS T S,DE MAST J.Quantifying the random component of measurement error of nominal measurements without a gold standard[J].Quality and Reliability Engineering International,2016,32(6):1993-2003. [13]JEONG S,LEE K.Spam Classification Based on Signed Net-work Analysis[J].Applied Sciences,2020,10(24):8952. [14]MADHAVAN V M,PANDE S,UMEKAR P,et al.Comparative Analysis of Detection of Email Spam With the Aid of Machine Learning Approaches[J].IOP Conference Series:Mate-rials Science and Engineering,2021,1022(1):012113. [15]XU C,SHEN X,ZHU L,et al.A Collusion-Resistant and Privacy-Preserving Data Aggregation Protocol in Crowdsensing System[J].Mobile Information Systems,2017,2017:1-11. [16]LI M,WENG J,YANG A,et al.CrowdBC:A blockchain-baseddecentralized framework for crowdsourcing[J].IEEE Transactions on Parallel and Distributed Systems,2018,30(6):1251-1266. [17]WANG Z,HU R,CHEN Q,et al.ColluEagle:collusive reviewspammer detection using Markov random fields[J].Data Mining and Knowledge Discovery,2020,34(6):1621-1641. [18]KUANG L,ZHANG H,SHI R,et al.A spam worker detection approach based on heterogeneous network embedding in crowdsourcing platforms[J].Computer Networks,2020,183:107587. [19]LUO J,SHAN H,ZHANG G,et al.Exploiting Syntactic and Semantic Information for Textual Similarity Estimation[J].Mathematical Problems in Engineering,2021,2021:4186750.1-4186750.12. [20]LAURIOLA I,LAVELLI A,AIOLLI F.An introduction todeep learning in natural language processing:models,techniques,and tools[J].Neurocomputing,2022,470:443-456. [21]OTT M,CARDIE C,HANCOCK J T.Negative deceptive opi-nion spam[C]//Proceedings of the 2013 Conference of the North Smerican Chapter of the Association for Computational Linguistics:Human Language Technologies.2013:497-501. [22]MUKHERJEE A,VENKATARAMAN V,LIU B,et al.Fake review detection:Classification and analysis of real and pseudo reviews:UIC-CS-03-2013[R].2013. |
|
||
首页