智慧群体所展现出兼具局部聚集性与全局整体性的结构状态引发了学界对其潜在机制的探查. 现有主流解释是基于社会资本的结构镶嵌和结构洞机制的组合, 对于基于个体属性的同质相吸和差异偏好机制的探讨相对不足. 此外, 相关工作往往采用多主体建模方法, 在一定程度上脱离了真实网络且不具备关系形成的预测能力. 对此, 本文运用数据分析与深度学习相结合的方法, 探查了同质相吸和差异偏好机制对于智慧群体结构演化的驱动作用. 研究结果表明, 本文所考察的两个不同领域智慧群体的协作网络经历三个阶段的演化后(即松散聚簇、 链状结构、 小世界状态), 展现出较好的局部聚集性与全局整体性. 其中, 同质相吸机制推动相似个体汇聚形成聚簇; 差异偏好机制促使聚簇间连接的形成. 研究结果不仅有助于进一步认识智慧群体结构演化的内在动力机制, 也为复杂网络结构演化机制的分析工作从深度学习视角提供了一个新的思路; 同时, 对于利用社会智力资源实施开放式创新的管理实践也具有一定的借鉴意义.
Abstract
The integration of local aggregation and global integrity in the structure of intelligent collectives arouses the exploration of its underlying mechanisms in the academic community. The current mainstream explanation is the combination of structural embeddedness and structural holes based on social capital, and the discussion of homophily and heterophily based on individual attributes is relatively insufficient. In addition, related work often adopts the method of agent-based modeling, which is divorced from the real network to a certain extent and cannot predict the formation of relationships. Accordingly, this paper uses the method of data analysis and deep learning to explore the driving role of homophily and heterophily in the structural evolution of intelligent collectives. The results show that the interactive networks of two intelligent groups in two different fields investigated in this paper have experienced three stages (namely, loose clustering, chain structure, and small world state), showing good local aggregation and global integrity. During the network evolution, homophily promotes similar individuals to converge and form clusters; heterophily promotes the formation of connections between clusters. This study not only helps to further understand the underlying mechanisms of the structural evolution in intelligent collectives, but also provides a new idea for the analysis of evolutionary mechanisms in complex networks from the perspective of deep learning. Meanwhile, our work also has certain reference significance for the management practice of using social intelligence resources to implement open innovation.
关键词
智慧群体 /
结构演化 /
深度学习 /
同质相吸 /
差异偏好
{{custom_keyword}} /
Key words
intelligent collectives /
structural evolution /
deep learning /
homophily /
heterophily
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Nguyen V D, Nguyen N T. Intelligent collectives:Theory, applications, and research challenges[J]. Cybernetics and Systems, 2018, 49(5-6):261-279.
[2] Liu J, Guo X, Xu S, et al. A new interpretation of scientific collaboration patterns from the perspective of symbiosis:An investigation for long-term collaboration in publications[J]. Journal of Informetrics, 2023, 17(1):101372.
[3] Pike T, Colter R, Bailey M, et al. Social networks as a collective intelligence:An examination of the python ecosystem[J]. arXiv preprint arXiv:2201.06040, 2022.
[4] Almaatouq A, Noriega-Campero A, Alotaibi A, et al. Adaptive social networks promote the wisdom of crowds[J]. Proceedings of the National Academy of Sciences, 2020, 117(21):11379-11386.
[5] 夏昊翔, 张潇, 张醒洲. OpenStack开源软件开发者协作网络分析[J]. 系统工程理论与实践, 2017, 37(5):1373-1382. Xia H X, Zhang X, Zhang X Z. Study on collaborative network of OpenStack OSS developers[J]. Systems Engineering——Theory & Practice, 2017, 37(5):1373-1382.
[6] Schilling M A, Phelps C C. Interfirm collaboration networks:The impact of large-scale network structure on firm innovation[J]. Management Science, 2007, 53(7):1113-1126.
[7] Behfar S K, Turkina E, Burger-Helmchen T. Knowledge management in OSS communities:Relationship between dense and sparse network structures[J]. International Journal of Information Management, 2018, 38(1):167-174.
[8] Behfar S K, Behfar Q. Intragroup density predicting intergroup tie strength within open-source-software collaboration network[C]//Distributed Computing and Artificial Intelligence, 13th International Conference, 2016:165-173.
[9] Moody J. The structure of a social science collaboration network:Disciplinary cohesion from 1963 to 1999[J]. American Sociological Review, 2004, 69(2):213-238.
[10] Uzzi B, Spiro J. Collaboration and creativity:The small world problem[J]. American Journal of Sociology, 2005, 111(2):447-504.
[11] Singh N P, Stout B D. Knowledge flow, innovative capabilities and business success:Performance of the relationship between small world networks to promote innovation[J]. International Journal of Innovation Management, 2018, 22(2):1850014.
[12] Eslami H, Ebadi A, Schiffauerova A. Effect of collaboration network structure on knowledge creation and technological performance:The case of biotechnology in Canada[J]. Scientometrics, 2013, 97:99-119.
[13] Granovetter M. Economic action and social structure:The problem of embeddedness[M]. American Journal of Sociology, 1985, 91(3):481-510.
[14] McPherson M, Smith-Lovin L, Cook J M. Birds of a feather:Homophily in social networks[J]. Annual Review of Sociology, 2001, 27(1):415-444.
[15] Backstrom L, Huttenlocher D, Kleinberg J, et al. Group formation in large social networks:Membership, growth, and evolution[C]//Proceedings of the 12th International Conference on Knowledge Discovery and Data Mining. 2006:44-54.
[16] Kumpula J M, Onnela J P, Saramäki J, et al. Emergence of communities in weighted networks[J]. Physical Review Letters, 2007, 99(22):228701.
[17] Cowan R, Jonard N, Zimmermann J B. Bilateral collaboration and the emergence of innovation networks[J]. Management Science, 2007, 53(7):1051-1067.
[18] Holme P, Newman M E J. Nonequilibrium phase transition in the coevolution of networks and opinions[J]. Physical Review E, 2006, 74(5):056108.
[19] Baum J A C, Cowan R, Jonard N. Network-independent partner selection and the evolution of innovation networks[J]. Management Science, 2010, 56(11):2094-2110.
[20] Girvan M, Newman M J. Community structure in social and biological networks[J]. Proceedings of the National Academy of Sciences, 2002, 99(12):7821-7826.
[21] Burt R S. Structural holes and good ideas[J]. American Journal of Sociology, 2004, 110(2):349-399.
[22] Watts D J, Strogatz S H. Collective dynamics of ‘small-world’ networks[J]. Nature, 1998, 393(6684):440-442.
[23] Park P S, Blumenstock J E, Macy M W. The strength of long-range ties in population-scale social networks[J]. Science, 2018, 362(6421):1410-1413.
[24] Rogers E M, Bhowmik D K. Homophily-heterophily:Relational concepts for communication research[J]. Public Opinion Quarterly, 1970, 34(4):523-538.
[25] 刘鹏, 张鹏臣, 王念新. 开源软件社区开发者协作网络结构演化分析——以Cloud Foundry社区为例[J]. 复杂系统与复杂性科学, 2019, 16(4):31-43. Liu P, Zhang P C, Wang N X. Structure and evolution on developer collaboration network in Cloud Foundry OSS community[J]. Complex Systems and Complexity Science, 2019, 16(4):31-43.
[26] Lee D, Goh K I, Kahng B, et al. Complete trails of coauthorship network evolution[J]. Physical Review E, 2010, 82(2):026112.
[27] Kimura D, Hayakawa Y. Coevolutionary networks with homophily and heterophily[J]. Physical Review E, 2008, 78(1):016103.
[28] Yuan Y, Alabdulkareem A, Pentland A S. An interpretable approach for social network formation among heterogeneous agents[J]. Nature Communications, 2018, 9(1):4704.
[29] Berahmand K, Nasiri E, Rostami M. et al. A modified DeepWalk method for link prediction in attributed social network[J]. Computing, 2021, 103(10):2227-2249.
[30] Liu P, Gui L, Wang H, et al. A two-stage deep-learning model for link prediction based on network structure and node attributes[J]. Sustainability, 2022, 14(23):16299.
[31] 曹志鹏, 潘定, 潘启亮. 基于表示学习的双层知识网络链路预测[J]. 情报学报, 2021, 40(2):135-144.Cao Z P, Pan D, Pan Q L. Link prediction in two-layer knowledge network based on network representation learning[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(2):135-144.
[32] 刘鹏, 夏昊翔. 跨学科研究领域的合著网络演化分析——以"复杂网络"研究领域为例[J]. 情报杂志, 2015(9):85-91.Liu P, Xia H X. The evolution of co-authorship network in the interdisciplinary research field of complex networks[J]. Journal of Intelligence, 2015(9):85-91.
[33] Scholl W. Effective teamwork——A theoretical model and a test in the field[M]. Understanding Group Behavior, Psychology Press, 2013:127-146.
[34] Gazni A, Sugimoto C R, Didegah F. Mapping world scientific collaboration:Authors, institutions, and countries[J]. Journal of the American Society for Information Science and Technology, 2012, 63(2):323-335.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金（71871108，71904043）
{{custom_fund}}
PDF(2777 KB)
