EvoInsight: A Conversational Framework for End-to-End Generation of Topic-Oriented Videos from Large-Scale Texts
Authors
Zongchao Dai (College of Intelligence and Computing), Chenyi Liu (College of Intelligence and Computing), Jie Li (College of Intelligence and Computing)
Presentation
- Session
- Let's dig into the data (from China)
- Time
- Friday, Nov 13, 09:12 – 09:24 (US/Eastern) · session 08:00 – 09:30
- Location
- Hall America center
Keywords
Text Visualization, Topic Modeling, Large Language Models, Multi-Agent, Visual Analytics
Abstract
Topic modeling is a fundamental technique for analyzing large-scale texts. However, its abstract and static outputs often impose a substantial cognitive burden on analysts. To bridge this gap, we propose EvoInsight, an LLM-based conversational visual analytics framework that transforms abstract topic evolution into dynamic data videos, termed Topic-Oriented Videos (TOVs). EvoInsight overcomes two primary limitations of existing data video techniques. First, existing tools rely on pre-defined narrative scripts, making them ill-suited for exploring unknown corpora. To address this, EvoInsight integrates an LLM-driven method that interactively discovers latent topics from a vectorized knowledge base, extracts relevant events, and organizes them into a coherent narrative backbone. Second, existing visualization techniques struggle to convey the complex, multi-entity relationships inherent in topic evolution. Therefore, our framework employs an end-to-end visual generation pipeline featuring multi-agent collaboration and image-to-image enhancement. This ensures semantic faithfulness and stylistic coherence across the generated video frames. Comprehensive evaluations, including a quantitative user study and qualitative domain-expert interviews, demonstrate that EvoInsight significantly outperforms ablations in narrative fluency and visual consistency, achieving quality comparable to human-crafted videos.
For Practitioners
Public-opinion analysts, data journalists, and video creators may benefit from this work. EvoInsight helps them discover topics from large-scale texts, organize evidence into coherent narratives, and generate topic-oriented videos through a conversational workflow. It can reduce the manual effort required for research, script writing, and visual production.