用多智能体LLM框架提升问卷分析的语义主题质量
MALTopic: Multi-Agent LLM Topic Modeling Framework
- 分角色智能体协作：补全结构化数据、提取主题、去重优化
- 相比LDA和BERTopic，主题连贯性、多样性与可读性均显著提升
- 适合需要精准解读复杂问卷数据的研究者或企业用户
主题建模是挖掘非结构化文本中潜在主题的关键技术，尤其在分析问卷回复时价值突出。但传统方法仅处理自由文本，未融合结构化或分类问卷数据，且生成的主题抽象难懂，需大量人工解读。为此，我们提出多智能体大模型主题建模框架MALTopic。该框架将主题建模分解为三个专责任务：由增强智能体利用结构化数据补充文本信息，主题建模智能体提取潜在主题，去重智能体优化结果。在问卷数据集上的对比实验表明，MALTopic在主题连贯性、多样性和可读性方面均显著优于LDA和BERTopic。通过融合结构化数据并采用多智能体架构，MALTopic生成更贴近语境、人类可读的主题，为复杂问卷数据分析提供了更高效解决方案。
原文摘要 · Abstract (English)
Topic modeling is a crucial technique for extracting latent themes from unstructured text data, particularly valuable in analyzing survey responses. However, traditional methods often only consider free-text responses and do not natively incorporate structured or categorical survey responses for topic modeling. And they produce abstract topics, requiring extensive human interpretation. To address these limitations, we propose the Multi-Agent LLM Topic Modeling Framework (MALTopic). This framework decomposes topic modeling into specialized tasks executed by individual LLM agents: an enrichment agent leverages structured data to enhance textual responses, a topic modeling agent extracts latent themes, and a deduplication agent refines the results. Comparative analysis on a survey dataset demonstrates that MALTopic significantly improves topic coherence, diversity, and interpretability compared to LDA and BERTopic. By integrating structured data and employing a multi-agent approach, MALTopic generates human-readable topics with enhanced contextual relevance, offering a more effective solution for analyzing complex survey data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。