军事知识服务平台
基于大语言模型和混合专家模型的社交机器人检测模型
A Social Bot Detection Model Based on Large Language Model and Mixture of Experts
摘要 [目的]针对现有社交机器人检测方法对文本内容中的语义差异区分不足、多源异构特征融合能力有限的问题,提出一种融合大语言模型与混合专家模型的社交机器人检测模型.[方法]首先,模型通过LLM2Vec嵌入用户帖子以捕捉语义层面的细微差别;其次,整合了6类特征体系(用户、好友、时间、内容、情感、AI)并利用混合专家模型的路由网络分配特征至对应专家网络层;最终,由特征融合模块整合多源特征用于社交机器人检测.[结果]在TwiBot-20和TwiBot-22两个公开数据集上的实验结果表明,所提模型的精确度分别达到0.821 0和0.775 6,整体性能优于对比模型,验证了该模型的有效性.[局限]未考察对抗攻击对模型鲁棒性的影响,也未深入讨论社交机器人误判可能引发的伦理风险.[结论]LLM2Vec有助于提取用户帖子中的语义信息,混合专家模型能够实现多源异构特征的差异化建模与有效融合,从而提升社交机器人检测性能.
Abstract:
[Objective]This study proposes a social bot detection model that integrates large language model representations with a mixture-of-experts model to address the limited ability to distinguish fine-grained semantic differences in textual content and fuse multi-source heterogeneous features.[Methods]The proposed model first uses LLM2Vec to embed user posts and capture fine-grained semantic differences.It then integrates six categories of features—user,social-network,temporal,content,sentiment,and AI-related features—and employs a routing network to dynamically assign them to the corresponding expert networks.[Results]Experimental results on two public datasets(TwiBot-20 and TwiBot-22)show that the proposed model achieves precisions of 0.8210 and 0.7756,respectively.Its overall performance surpasses that of the comparison models,thus validating the effectiveness of the proposed model.[Limitations]This study has not yet examined the impact of adversarial attacks on model robustness or thoroughly discussed the ethical risks that may arise from the misclassification of social bots.[Conclusions]LLM2Vec facilitates the extraction of semantic information from user posts,while the mixture-of-experts model enables differentiated modeling and the effective fusion of multi-source heterogeneous features,thereby improving the performance of social bot detection.
刊 名 数据分析与知识发现 ISTICEIPKU
年,卷(期): 2026, 10(7)
分类号: TP391.1
机标分类号: TP391.41 TN92 S718.5
在线出版日期: 2026年10月10日