VizTA: Enhancing Comprehension of Distributional Visualization with Visual-Lexical Fused Conversational Interface

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Liangwei, Wang, Zhan, Xiao, Shishi, Liu, Le, Tsung, Fugee, Zeng, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908328463958016
author Wang, Liangwei
Wang, Zhan
Xiao, Shishi
Liu, Le
Tsung, Fugee
Zeng, Wei
author_facet Wang, Liangwei
Wang, Zhan
Xiao, Shishi
Liu, Le
Tsung, Fugee
Zeng, Wei
contents Comprehending visualizations requires readers to interpret visual encoding and the underlying meanings actively. This poses challenges for visualization novices, particularly when interpreting distributional visualizations that depict statistical uncertainty. Advancements in LLM-based conversational interfaces show promise in promoting visualization comprehension. However, they fail to provide contextual explanations at fine-grained granularity, and chart readers are still required to mentally bridge visual information and textual explanations during conversations. Our formative study highlights the expectations for both lexical and visual feedback, as well as the importance of explicitly linking these two modalities throughout the conversation. The findings motivate the design of VizTA, a visualization teaching assistant that leverages the fusion of visual and lexical feedback to help readers better comprehend visualization. VizTA features a semantic-aware conversational agent capable of explaining contextual information within visualizations and employs a visual-lexical fusion design to facilitate chart-centered conversation. A between-subject study with 24 participants demonstrates the effectiveness of VizTA in supporting the understanding and reasoning tasks of distributional visualization across multiple scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14507
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VizTA: Enhancing Comprehension of Distributional Visualization with Visual-Lexical Fused Conversational Interface
Wang, Liangwei
Wang, Zhan
Xiao, Shishi
Liu, Le
Tsung, Fugee
Zeng, Wei
Human-Computer Interaction
Comprehending visualizations requires readers to interpret visual encoding and the underlying meanings actively. This poses challenges for visualization novices, particularly when interpreting distributional visualizations that depict statistical uncertainty. Advancements in LLM-based conversational interfaces show promise in promoting visualization comprehension. However, they fail to provide contextual explanations at fine-grained granularity, and chart readers are still required to mentally bridge visual information and textual explanations during conversations. Our formative study highlights the expectations for both lexical and visual feedback, as well as the importance of explicitly linking these two modalities throughout the conversation. The findings motivate the design of VizTA, a visualization teaching assistant that leverages the fusion of visual and lexical feedback to help readers better comprehend visualization. VizTA features a semantic-aware conversational agent capable of explaining contextual information within visualizations and employs a visual-lexical fusion design to facilitate chart-centered conversation. A between-subject study with 24 participants demonstrates the effectiveness of VizTA in supporting the understanding and reasoning tasks of distributional visualization across multiple scenarios.
title VizTA: Enhancing Comprehension of Distributional Visualization with Visual-Lexical Fused Conversational Interface
topic Human-Computer Interaction
url https://arxiv.org/abs/2504.14507