An Evaluation-Focused Framework for Visualization Recommendation Algorithms ------------------------------------------------------------------------ ### **demo_video.mp4** A demonstration video of the interface, including user study procedures and the functionalities of the system. ### **interface_code** This folder contains the code for the interface design used in the empirical user study. The interface is implemented using Python Flask for the backend and HTML, CSS, JavaScript for the frontend. - **`app.py`**: the Flask application - **web**: - **static**: stores all static files, like datasets, as well as CSS and JavaScript files - **templates**: stores all HTML files. ### **analysis_code** This folder contains the aggregated results from the experiment and the R scripts for analyzing the data. The `.Rmd` (RMarkdown) files are source code. The `.html` files are compiled outputs for better reading experience. The models folder contains all the fitted brms models. - **data**: The aggregated results from the user study evaluating and comparing four visualization recommendation algorithms.\ \ Data Columns: - **participant_id**: an anonymous and unique ID assigned to each participant - **participant_group**: records the participant belongs to which group, student or professional - **dataset**: records which dataset the participant was exposed to - **oracle**: records the oracle of the recommendation algorithm that provided recommendations - **search**: records the search method of the recommendation algorithm that provided recommendations - **task**: records the current task - **{accuracy_analysis|interaction|time_analysis|user_response}.{Rmd|html}**: analysis scripts - **`helper_functions.R`**: helper functions for generating plots