{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T21:03:52Z","timestamp":1778619832374,"version":"3.51.4"},"reference-count":37,"publisher":"Tsinghua University Press","issue":"2","license":[{"start":{"date-parts":[[2017,6,12]],"date-time":"2017-06-12T00:00:00Z","timestamp":1497225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJCS"],"published-print":{"date-parts":[[2017,6,12]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>Allocation of complex crowdsourcing tasks, which typically include heterogeneous attributes such as value, difficulty, skill required, effort required and deadline, is still a challenging open problem. In recent years, agent-based crowdsourcing approaches focusing on recommendations or incentives have emerged to dynamically match workers with diverse characteristics to tasks to achieve high collective productivity. However, existing approaches are mostly designed based on expert knowledge grounded in well-established theoretical frameworks. They often fail to leverage on user-generated data to capture the complex interaction of crowdsourcing participants\u2019 behaviours. This paper aims to address this challenge.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>The paper proposes a policy network plus reputation network (PNRN) approach which combines supervised learning and reinforcement learning to imitate human task allocation strategies which beat artificial intelligence strategies in this large-scale empirical study. The proposed approach incorporates a policy network for the selection of task allocation strategies and a reputation network for calculating the trends of worker reputation fluctuations. Then, by iteratively applying the policy network and reputation network, a multi-round allocation strategy is proposed.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>PNRN has been trained and evaluated using a large-scale real human task allocation strategy data set derived from the Agile Manager game with close to 500,000 decision records from 1,144 players in over 9,000 game sessions. Extensive experiments demonstrate the validity and efficiency of computational complex crowdsourcing task allocation strategy learned from human participants.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>The paper can give a better task allocation strategy in the crowdsourcing systems.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/ijcs-08-2017-0011","type":"journal-article","created":{"date-parts":[[2017,11,15]],"date-time":"2017-11-15T13:34:00Z","timestamp":1510752840000},"page":"146-160","source":"Crossref","is-referenced-by-count":4,"title":["Complex crowdsourcing task allocation strategies employing supervised and reinforcement learning"],"prefix":"10.26599","volume":"1","author":[{"given":"Lizhen","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"11138","reference":[{"key":"ref33","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-014-9423-5"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref30","author":"dan","year":"2012","journal-title":"Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2059690"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.14778\/2536336.2536337"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2016.04.020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbv021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2016.12"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2015.46"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.14778\/2336664.2336676"},{"key":"ref14","article-title":"A distributed anytime algorithm for dynamic task allocation in multi-agent systems","author":"macarthur","year":"0","journal-title":"Proceedings of the 25th AAAI Conference on Artificial Intelligence (AAAI-11)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2010.11.033"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2016.06.019"},{"key":"ref17","first-page":"469","article-title":"Productive output in hierarchical crowdsourcing","author":"nath","year":"0","journal-title":"Proceedings of the 13th International Conference on Autonomous Agents and Multi-agent Systems (AAMAS'14)"},{"key":"ref18","first-page":"477","article-title":"Budgetfix: budget limited crowdsourcing for interdependent task allocation with quality guarantees","author":"tran-thanh","year":"0","journal-title":"Proceedings of the 1st International Conference on Autonomous Agents and Multi-Agent Systems"},{"key":"ref19","first-page":"901","article-title":"Efficient budget allocation with accuracy guarantees for crowdsourcing classification tasks","author":"tran-thanh","year":"0","journal-title":"Proceedings of the 12th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'13)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.127"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref27","first-page":"1315","article-title":"A reputation-aware decision-making approach for improving the efficiency of crowdsourcing systems","author":"yu","year":"0","journal-title":"Proceedings of the 12th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'13)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8120"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0954-1810(94)00011-S"},{"key":"ref29","first-page":"1661","article-title":"A multi-agent game for studying human decision-making","author":"yu","year":"0","journal-title":"Proceedings of the 13th International Conference on Autonomous Agents and Multi-agent Systems (AAMAS'14)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1109672110"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2005.05.019"},{"key":"ref7","first-page":"2492","article-title":"Reputation-based worker filtering in crowdsourcing","author":"jagabathula","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2012.6234604"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9945"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2015.03.004"},{"key":"ref20","first-page":"418","article-title":"A reputation management approach for resource constrained trustee agents","author":"yu","year":"0","journal-title":"Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI'13)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-016-0011-6"},{"key":"ref21","first-page":"357","article-title":"Reputation-aware task allocation for human trustees","author":"yu","year":"0","journal-title":"Proceedings of the 1st International Conference on Autonomous Agents and Multi-Agent Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9337"},{"key":"ref23","first-page":"1689","article-title":"Quality and budget aware task allocation for spatial crowdsourcing","author":"yu","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2012.104"},{"key":"ref25","first-page":"1687","article-title":"Empirical analysis of reputation-aware task delegation by humans from a multi-agent game","author":"yu","year":"0","journal-title":"Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS'15)"}],"container-title":["International Journal of Crowd Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJCS-08-2017-0011\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJCS-08-2017-0011\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,18]],"date-time":"2022-08-18T16:00:29Z","timestamp":1660838429000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJCS-08-2017-0011\/full\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,12]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,6,12]]}},"alternative-id":["10.1108\/IJCS-08-2017-0011"],"URL":"https:\/\/doi.org\/10.1108\/ijcs-08-2017-0011","relation":{},"ISSN":["2398-7294"],"issn-type":[{"value":"2398-7294","type":"print"}],"subject":[],"published":{"date-parts":[[2017,6,12]]}}}