What’s Your VATI? Understanding Attraction Profiles for Data Visualization on Social Media
Authors
Chuyi Zheng (Tongji University), Zikai Li (Tongji University), Zijian Yang (Tongji University), Shenghong Li (Shanghai Jiao Tong University), Lixing Chen (Shanghai Jiao Tong University), Yang Shi (Tongji University)
Presentation
- Session
- Let's dig into the data (from France)
- Time
- Wednesday, Nov 11, 08:36 – 08:48 (US/Eastern) · session 08:00 – 09:30
- Location
- Hall America north
Keywords
Attraction profiles, social media visualization, user modeling
Abstract
Data visualizations on social media are often encountered as small thumbnails embedded in rapidly scrolling feeds. These entry-stage visualizations can elicit markedly different responses across users, yet little is known about how to systematically characterize such heterogeneity. We introduce attraction profiles, a user-level construct capturing consistent tendencies in first-exposure interactions with visualization thumbnails. To study these profiles, we construct a dataset of 1,349 thumbnails from authoritative news organizations and record click behaviors from 800 participants in a feed-style browsing study. Using this dataset, we develop the Attraction Profile Modeling Framework, which extracts visual and textual features and decouples topical influences to infer content-independent user representations. Based on these profiles, we introduce the Visualization Attraction Type Indicator (VATI), a structured typology that applies Exploratory Factor Analysis to uncover latent factors and maps them to five interpretable dimensions: Analytical Depth, Epistemic Drive, Visual Complexity Sensitivity, Figurative Tendency, and Structural Dependence. Each user is represented as a vector along these dimensions, enabling systematic comparison. Evaluation through ablation and user studies shows that APM captures intrinsic attraction patterns, while VATI provides an interpretable representation of multidimensional user tendencies.
For Practitioners
This work is intended for data journalists, visualization designers, and social media content teams who create chart thumbnails for feed-style distribution, as well as HCI researchers and platform teams building personalized visualization recommendation systems. Practitioners can use the five VATI dimensions as a lightweight, interpretable diagnostic when designing or A/B testing thumbnails—for example, pairing a low-complexity entry-point design with a denser, more analytical full article to balance attraction and information integrity. Recommendation system designers can treat VATI scores as user-level style features for personalizing presentation format without narrowing topical diversity, mitigating the filter-bubble risk.