WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
Yuntian Deng, Wenting Zhao, Jack Hessel, Xiang Ren, Claire Cardie,, Yejin Choi

TL;DR
WildVis is an open-source visualization tool designed for efficient analysis of large-scale chat logs, enabling researchers to explore and compare conversations at the million-scale with fast search and visualization features.
Contribution
The paper introduces WildVis, a novel interactive tool that handles million-scale conversation datasets with optimized search, embedding, and caching for rapid analysis and visualization.
Findings
WildVis enables rapid exploration of large chat datasets.
It facilitates research on chatbot misuse and conversation patterns.
The tool is open-source and extendable.
Abstract
The increasing availability of real-world conversation data offers exciting opportunities for researchers to study user-chatbot interactions. However, the sheer volume of this data makes manually examining individual conversations impractical. To overcome this challenge, we introduce WildVis, an interactive tool that enables fast, versatile, and large-scale conversation analysis. WildVis provides search and visualization capabilities in the text and embedding spaces based on a list of criteria. To manage million-scale datasets, we implemented optimizations including search index construction, embedding precomputation and compression, and caching to ensure responsive user interactions within seconds. We demonstrate WildVis' utility through three case studies: facilitating chatbot misuse research, visualizing and comparing topic distributions across datasets, and characterizing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsSocial Media and Politics
