【摘要】 随着社会的不断进步和网络技术的发展，新闻传播模型中网络社团的规模不断加大，网络结构更加复杂。本研究探讨了多目标进化算法原理，分析了网络社团的结构，提出了基于社团结构节点属性信息的多目标进化社团自动检测算法(Automatic detection algorithm of multi-objective evolutionary community MOEA-AT)。测试结果表明，MOEA-AT算法的NMI,AC和Q的平均值分别为0.95、0.92、0.89,各指标的均值较高，在实际网络中表现较好。应用于真实网络时，MOEA-AT算法将网络划分成2～5个社团，且社团之间界限较为清楚。由此可知，MOEA-AT算法对网络社团的自动检测有更高的精度且稳定性更高，并且在新闻传播领域有一定的现实意义和经济价值。更多还原

【Abstract】 With the continuous progress of the society and the development of the network technology, the scale of the network community in the news communication model is increasing, and the network structure is more complex. In this study, we analyzed the structure of network community structure, analyzed the principle of multi-objective evolution algorithm, and proposed the automatic detection algorithm(Automatic detection algorithm of multi-objective evolutionary community MOEA-AT) based on the node information attribute of community structure. The test results show that the NMI, AC and Q of MOEA-AT algorithm mean value are 0.95,0.92 and 0.89 respectively, and the mean value of each index is high and performs well in the real network. When applied to the actual network, the MOEA-AT algorithm divides the real network into 2-5 associations, and the boundary between the associations is relatively clear. It can be seen that MOEA-AT algorithm has higher accuracy and better stability for the automatic detection of network associations, and has certain practical significance and economic value in the field of news communication.更多还原