Top > JACIII > Multi-Team Formation System for Collaborative Crowdsourcing

single-jc.php

JACIII Vol.30 No.2 pp. 509-522
(2026)
doi: 10.20965/jaciii.2026.p0509

Research Paper:

Views over last 60 days: 3,459

Multi-Team Formation System for Collaborative Crowdsourcing

Ryota Yamamoto and Kazushi Okamoto ORCID Icon

Department of Informatics, Graduate School of Informatics and Engineering, The University of Electro-Communications
1-5-1 Chofugaoka, Chofu, Tokyo 182-8585, Japan

Received:
May 15, 2025
Accepted:
November 3, 2025
Published:
March 20, 2026
Creative Commons License
Keywords:
crowdsourcing, social network, combinatorial optimization, metaheuristics
Abstract

For complex crowdsourcing tasks that require collaboration among multiple individuals, teams should be formed by considering both worker compatibility and expertise. Furthermore, the nature of crowdsourcing dictates the budget for tasks and worker remuneration, and excessively large teams may reduce collaborative performance. To address these challenges, we propose a heuristic optimization algorithm that leverages social network information to simultaneously form teams with optimized worker compatibility for multiple tasks. In our approach, historical collaboration is represented as a social network in which the edge weights correspond to the explicit ratings of worker compatibility. In a simulation experiment using synthetic data, we applied Gaussian process regression to examine the relationship between the eight experimental parameters and evaluation values, thereby analyzing the output of the proposed algorithm. To generate the data necessary for regression, we ran the proposed algorithm with experimental parameters that were sequentially estimated using Bayesian optimization. Our experiments revealed that the evaluation values were extremely low when the team size limit, degree mean of the social network, and task budget were set to low values. The results also indicate that the proposed algorithm outperforms the hill-climbing method under almost all experimental conditions. In addition, the highest evaluation values were achieved when the simulated annealing temperature decreased at a rate of approximately 0.9, whereas smoothing the objective function proved to be ineffective.

Full text
Cite this article as:
R. Yamamoto and K. Okamoto, “Multi-Team Formation System for Collaborative Crowdsourcing,” J. Adv. Comput. Intell. Intell. Inform., Vol.30 No.2, pp. 509-522, 2026.
Data files:
References
  1. [1] K. Kashima, S. Oyama, and B. Yukino, “Human Computation and Crowdsourcing, 1st ed.,” Kodansha, 2016.
  2. [2] G. Hertel, “Synergetic effects in working teams,” J. of Managerial Psychology, Vol.26, No.3, pp. 176-184, 2011. https://doi.org/10.1108/02683941111112622
  3. [3] J. Hüffmeier and G. Hertel, “When the whole is more than the sum of its parts: Group motivation gains in the wild,” J. of Experimental Social Psychology, Vol.47, No.2, pp. 455-459, 2011. https://doi.org/10.1016/j.jesp.2010.12.004
  4. [4] I. Lykourentzou, A. Antoniou, Y. Naudet, and S. P. Dow, “Personality matters: Balancing for personality types leads to better outcomes for crowd teams,” Proc. of the 19th ACM Conf. on Computer-Supported Cooperative Work & Social Computing, pp. 260-273, 2016. https://doi.org/10.1145/2818048.2819979
  5. [5] K. L. Smart and C. Barnum, “Communication in cross-functional teams: an introduction to this special issue,” IEEE Trans. on Professional Communication, Vol.43, No.1, pp. 19-21, 2000. https://doi.org/10.1109/TPC.2000.826413
  6. [6] A. Majumder, S. Datta, and K. V. M. Naidu, “Capacitated team formation problem on social networks,” Proc. of the 18th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, pp. 1005-1013, 2012. https://doi.org/10.1145/2339530.2339690
  7. [7] R. Kenna and B. Berche, “Managing research quality: critical mass and optimal academic research group size,” IMA J. of Management Mathematics, Vol.23, No.2, pp. 195-207, 2011. https://doi.org/10.1093/imaman/dpr021
  8. [8] F. Khatib, F. DiMaio, F. C. Group, F. V. C. Group, S. Cooper, M. Kazmierczyk, M. Gilski, S. Krzywda, H. Zabranska, I. Pichova, J. Thompson, Z. Popović, M. Jaskolski, and D. Baker, “Crystal structure of a monomeric retroviral protease solved by protein folding game players,” Nature Structural & Molecular Biology, Vol.18, No.10, pp. 1175-1177, 2011. https://doi.org/10.1038/nsmb.2119
  9. [9] T. Lappas, K. Liu, and E. Terzi, “Finding a team of experts in social networks,” Proc. of the 15th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, pp. 467-476, 2009. https://doi.org/10.1145/1557019.1557074
  10. [10] C.-T. Li and M.-K. Shan, “Team formation for generalized tasks in expertise social networks,” Proc. of the IEEE 2nd Int. Conf. on Social Computing, pp. 9-16, 2010. https://doi.org/10.1109/SocialCom.2010.12
  11. [11] A. Gajewar and A. D. Sarma, “Multi-skill collaborative teams based on densest subgraphs,” Proc. of the 2012 SIAM Int. Conf. on Data Mining (SDM), pp. 165-176, 2012. https://doi.org/10.1137/1.9781611972825.15
  12. [12] G. K. Awal and K. K. Bharadwaj, “Team formation in social networks based on collective intelligence—An evolutionary approach,” Applied Intelligence, Vol.41, No.2, pp. 627-648, 2014. https://doi.org/10.1007/s10489-014-0528-y
  13. [13] M.-C. Juang, C.-C. Huang, and J.-L. Huang, “Efficient algorithms for team formation with a leader in social networks,” The J. of Supercomputing, Vol.66, No.2, pp. 721-737, 2013. https://doi.org/10.1007/s11227-013-0907-x
  14. [14] K. Selvarajah, P. M. Zadeh, Z. Kobti, Y. Palanichamy, and M. Kargar, “A unified framework for effective team formation in social networks,” Expert Systems with Applications, Vol.177, Article No.114886, 2021. https://doi.org/10.1016/j.eswa.2021.114886
  15. [15] C.-T. Li, M.-K. Shan, and S.-D. Lin, “On team formation with expertise query in collaborative social networks,” Knowledge and Information Systems, Vol.42, No.2, pp. 441-463, 2015. https://doi.org/10.1007/s10115-013-0695-x
  16. [16] C. Dorn and S. Dustdar, “Composing near-optimal expert teams: A trade-off between skills and connectivity,” On the Move to Meaningful Internet Systems (OTM 2010), pp. 472-489, 2010. https://doi.org/10.1007/978-3-642-16934-2_35
  17. [17] F. Farhadi, M. Sorkhi, S. Hashemi, and A. Hamzeh, “An effective expert team formation in social networks based on skill grading,” Proc. of the IEEE 11th Int. Conf. on Data Mining Workshops, pp. 366-372, 2011. https://doi.org/10.1109/ICDMW.2011.28
  18. [18] C. Dorn, F. Skopik, D. Schall, and S. Dustdar, “Interaction mining and skill-dependent recommendations for multi-objective team composition,” Data & Knowledge Engineering, Vol.70, No.10, pp. 866-891, 2011. https://doi.org/10.1016/j.datak.2011.06.004
  19. [19] M. Kargar, A. An, and M. Zihayat, “Efficient bi-objective team formation in social networks,” Machine Learning and Knowledge Discovery in Databases, pp. 483-498, 2012. https://doi.org/10.1007/978-3-642-33486-3_31
  20. [20] M. Kargar, M. Zihayat, and A. An, “Finding affordable and collaborative teams from a network of experts,” Proc. of the 2013 SIAM Int. Conf. on Data Mining, pp. 587-595, 2013. https://doi.org/10.1137/1.9781611972832.65
  21. [21] A. Anagnostopoulos, L. Becchetti, C. Castillo, A. Gionis, and S. Leonardi, “Online team formation in social networks,” Proc. of the 21st Int. Conf. on World Wide Web, pp. 839-848, 2012. https://doi.org/10.1145/2187836.2187950
  22. [22] S. S. Rangapuram, T. Bühler, and M. Hein, “Towards realistic team formation in social networks based on densest subgraphs,” Proc. of the 22nd Int. Conf. on World Wide Web, pp. 1077-1088, 2013. https://doi.org/10.1145/2488388.2488482
  23. [23] Y. Yang and H. Hu, “Team formation with time limit in social networks,” Proc. 2013 Int. Conf. on Mechatronic Sciences, Electric Engineering and Computer, pp. 1590-1594, 2013. https://doi.org/10.1109/MEC.2013.6885315
  24. [24] L. Chen, Y. Ye, A. Zheng, F. Xie, Z. Zheng, and M. R. Lyu, “Incorporating geographical location for team formation in social coding sites,” World Wide Web, Vol.23, No.1, pp. 153-174, 2020. https://doi.org/10.1007/s11280-019-00712-x
  25. [25] K. Selvarajah, A. Bhullar, Z. Kobti, and M. Kargar, “WSCAN-TFP: Weighted scan clustering algorithm for team formation problem in social network,” Proc. of the 31st Int. Florida Artificial Intelligence Research Society Conf., pp. 209-212, 2018.
  26. [26] K. Selvarajah, P. M. Zadeh, M. Kargar, and Z. Kobti, “Identifying a team of experts in social networks using a cultural algorithm,” Procedia Computer Science, Vol.151, pp. 477-484, 2019. https://doi.org/10.1016/j.procs.2019.04.065
  27. [27] H. Rahman, S. B. Roy, S. Thirumuruganathan, S. Amer-Yahia, and G. Das, “Task assignment optimization in collaborative crowdsourcing,” Proc. of the 2015 IEEE Int. Conf. on Data Mining, pp. 949-954, 2015. https://doi.org/10.1109/ICDM.2015.119
  28. [28] Y. Sun, W. Tan, and Q. Zhang, “An efficient algorithm for crowdsourcing workflow tasks to social networks,” Proc. of the IEEE 20th Int. Conf. on Computer Supported Cooperative Work in Design, pp. 532-538, 2016. https://doi.org/10.1109/CSCWD.2016.7566046
  29. [29] R. Yamamoto and K. Okamoto, “Worker organization system for collaborative crowdsourcing,” Intelligent and Transformative Production in Pandemic Times, pp. 13-22, 2023. https://doi.org/10.1007/978-3-031-18641-7_2
  30. [30] A. Yadav, A. S. Sairam, and A. Kumar, “Concurrent team formation for multiple tasks in crowdsourcing platform,” Proc. of the 2017 IEEE Global Communications Conf., 2017. https://doi.org/10.1109/GLOCOM.2017.8255048
  31. [31] Q. Liu, T. Luo, R. Tang, and S. Bressan, “An efficient and truthful pricing mechanism for team formation in crowdsourcing markets,” Proc. of the 2015 IEEE Int. Conf. on Communications (ICC), pp. 567-572, 2015. https://doi.org/10.1109/ICC.2015.7248382
  32. [32] W. Wang, J. Jiang, B. An, Y. Jiang, and B. Chen, “Toward efficient team formation for crowdsourcing in noncooperative social networks,” IEEE Trans. on Cybernetics, Vol.47, No.12, pp. 4208-4222, 2017. https://doi.org/10.1109/TCYB.2016.2602498
  33. [33] G. Barnabò, A. Fazzone, S. Leonardi, and C. Schwiegelshohn, “Algorithms for fair team formation in online labour marketplaces,” Companion Proc. of The 2019 World Wide Web Conf., pp. 484-490, 2019. https://doi.org/10.1145/3308560.3317587
  34. [34] W. Chen, J. Yang, and Y. Yu, “Analysis on communication cost and team performance in team formation problem,” Collaborative Computing: Networking, Applications and Worksharing, pp. 435-443, 2018. https://doi.org/10.1007/978-3-030-00916-8_41
  35. [35] M. Kargar and A. An, “Discovering top-k teams of experts with/without a leader in social networks,” Proc. of the 20th ACM Int. Conf. on Information and Knowledge Management, pp. 985-994, 2011. https://doi.org/10.1145/2063576.2063718
  36. [36] A. Lancichinetti, S. Fortunato, and F. Radicchi, “Benchmark graphs for testing community detection algorithms,” Physical Review E, Vol.78, No.4, Article No.046110, 2008. https://doi.org/10.1103/PhysRevE.78.046110
  37. [37] N. Tamura and M. Banbara, “Sugar: A csp to sat translator based on order encoding,” Proc. of the 2nd Int. CSP Solver Competition, pp. 65-69, 2008.
  38. [38] R. Yamamoto and K. Okamoto, “An algorithm for solving constraint satisfaction problems in concurrent formation of expert teams,” IEICE Trans. on Information and Systems (Japanese Edition), Vol.J107-D, No.3, pp. 87-97, 2024 (in Japanese). https://doi.org/10.14923/transinfj.2023JDP7006

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Mar. 19, 2026