Information Systems and Technology
Permanent URI for this collection
Browse
Browsing Information Systems and Technology by Author "Hoque Prince, Enamul"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Deconstructing And Restyling SVG Charts Using Large Language Models(2025-04-10) Zaidi, Syed Muhammad Ali Raza; Hoque Prince, EnamulSVG charts are very common on the Web, however, reusing, editing and restyling these charts is very difficult. To facilitate this process, this thesis explores the challenges of extracting data and visual encodings from SVG chart images and restyling them based on user queries. We leverage large language models (LLMs) to facilitate this process using few-shot prompt approaches, enabling users to deconstruct and restyle existing Vega-Lite visualizations through natural language input. Our evaluation on 800 SVG charts and 250 natural language queries reveals that our system accurately deconstruct 93.4% charts and successfully restyled 38.6% queries. Finally, based on the above techniques, we develop a Chrome plugin tool that detects and deconstructs SVG charts from the web page and then restyles the charts based on user input.Item Open Access Exploring the Effect of User Characteristics in Word Cloud Visualizations(2022-08-08) Shirin, Zehra; Hoque Prince, EnamulWord clouds are very popular for visually summarizing texts. While word clouds usually show the frequency of words using font size, recent studies have explored other possible design elements. However, there is still a gap in terms of understanding how individual differences among users may impact their performance. This thesis aims to bridge this gap by answering two key research questions: What user characteristics are impacted by different variations of word clouds, and how word clouds could be adapted to different user characteristics. To answer these questions, we ran a user study where participants performed perceptual speed and verbal working memory tests followed by 36 trials of the magnitude judgement task for word clouds. Results showed that user characteristics like perceptual speed can significantly impact the performance of users. These results can be useful in the future to provide personalized word clouds that are suitable for people with different user characteristics.