Aidan Slingsby

Steering the transition: A visual analytics approach to interactive energy scenario modeling

Dany Laksono, Radu Jianu, Aidan Slingsby

HighlightsVisual analytics framework for human-in-the-loop energy scenario modeling.• Modular "Filter-Prioritize-Upgrade" workflow replaces black-box optimization.• Multivariate glyphs and streamgraphs consolidate high-dimensional energy data.• Synchronized comparison mode enables side-by-side evaluation of policy plans.• Provenance tracking via remote database supports persistent strategy auditing.

us, gb (code pays fourni par la source)

InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations

Maeve Hutchinson, S. Huq, Mohammad Albinhassan, Radu Jianu et autres

Vision Language Models have demonstrated remarkable proficiency in interpreting static visual artifacts, but modern data analysis is inherently dynamic, requiring the active interrogation of interactive environments. Existing benchmarks are predominantly constrained to static imagery and one-shot question answering and fail to capture …

Foreword to the Computer Graphics & Visual Computing conference 2024 special section

Aidan Slingsby, Mai Elshehaly, Kai Xu

us, gb (code pays fourni par la source)

Discovering City-Scale Mobility Reconfigurations via Topic Modelling of Extreme Flows

Laleh Moussavi, Gennady Andrienko, Natalia Andrienko, Aidan Slingsby

Urban mobility is typically analysed through averages and long-term trends, yet the most informative behavioural signals often occur during periods of disruption. Strikes, extreme weather, holidays, and societal shocks do not simply alter volumes; they reconfigure the spatial structure of movement. Identifying …

Interactive Decision Support for Exploratory Planning of EV Charging Infrastructure

Dany Laksono, Radu Jianu, Aidan Slingsby

Urban infrastructure planning, such as Electric Vehicle Charging Point (EVCP) siting, requires balancing complex trade-offs between accessibility, grid capacity, and equity. We present an interactive visual analytics platform that supports real-time Multi-criteria Decision Analysis (MCDA). The system integrates parallel coordinate weight controls, …

What Do LLMs Prioritise When Adapting Visualizations to User Personas?

Amir Hosseini, Jo Wood, Aidan Slingsby, Radu Jianu et autres

Large Language Models (LLMs) are increasingly used for generating and adapting visualizations for different user groups. While recent efforts have focused on adapting visualizations to users’ cognitive and perceptual abilities, how LLMs cater to the distinct interests and subjective priorities of various …

gb (code pays fourni par la source)

Capturing Visualization Design Rationale

Maeve Hutchinson, Radu Jianu, Aidan Slingsby, Jo Wood et autres

Prior natural language datasets for data visualization have focused on tasks such as visualization literacy assessment, insight generation, and visualization generation from natural language instructions. These studies often rely on controlled setups with purpose-built visualizations and artificially constructed questions. As a result, …

gb (code pays fourni par la source)

Designing for Collaboration: Visualization to Enable Human–LLM Analytical Partnership

Mai Elshehaly, Radu Jianu, Aidan Slingsby, Gennady Andrienko et autres

Visualization artifacts have long served as anchors for collaboration and knowledge transfer in data analysis. While effective for human-human collaboration, little is known about their role in capturing and externalizing knowledge when working with large language models (LLMs). Despite the growing role …

gb (code pays fourni par la source)

Chart Question Answering from Real-World Analytical Narratives

Maeve Hutchinson, Radu Jianu, Aidan Slingsby, Jo Wood et autres

We present a new dataset for chart question answering (CQA) constructed from visualization notebooks. The dataset features real-world, multi-view charts paired with natural language questions grounded in analytical narratives. Unlike prior benchmarks, our data reflects ecologically valid reasoning workflows. Benchmarking state-of-the-art multimodal …

Capturing Visualization Design Rationale

Maeve Hutchinson, Radu Jianu, Aidan Slingsby, Jo Ann Wood et autres

Prior natural language datasets for data visualization have focused on tasks such as visualization literacy assessment, insight generation, and visualization generation from natural language instructions. These studies often rely on controlled setups with purpose-built visualizations and artificially constructed questions. As a result, …

Foundation model assisted visual analytics: Opportunities and Challenges

Maeve Hutchinson, Radu Jianu, Aidan Slingsby, Pranava Madhyastha

We explore the integration of foundation models, such as large language models (LLMs) and multimodal LLMs (MLLMs), into visual analytics (VA) systems through intuitive natural language interactions. We survey current research directions in this emerging field, examining how foundation models have already …

us, gb (code pays fourni par la source)

Visually-supported topic modeling for understanding behavioral patterns from spatio–temporal events

Laleh Moussavi, Gennady Andrienko, Natalia V. Andrienko, Aidan Slingsby

Spatio-temporal event sequences consist of activities or occurrences involving various interconnected elements in space and time. We show how topic modeling—typically used in text analysis—can be adapted to abstract and conceptualize such data. We propose an overall analytical workflow that combines computational …

gb, de (code pays fourni par la source)