Modeling How Different User Groups Perceive Webpage Aesthetics

Abstract

Aesthetics is a central consideration in user interface design. It is known to affect end-user behavior and perception, in particular the first impression of graphical user interfaces. However, what users perceive as pleasant or good design is highly subjective. We contribute a computational model that estimates the visual appeal of a given webpage for several common cohorts, or user groups, including gender, age, and education level. Our model, a convolutional neural network trained on 418 webpage screenshots having 771k aesthetic scores (in a 1-9 Likert scale) from 32k users, achieves high accuracy and is always less than 1 point off from ground-truth ratings. Designers can use our model to anticipate how people would rate their webpage, offer personalized designs according to the visual preferences of their users, and support rapid evaluations of webpage design prototypes for specific cohorts.

Research highlights

• A computational model that estimates the visual appeal of a given webpage for several cohorts, i.e. user groups or profiles.
• The model is highly accurate and always less than 1 point off from ground-truth scores (ranged between 1 and 9).

Resources

• Paper
• Training software

The provided software will generate the model files (.h5 file extension) we used in our paper. Please read the README.md file for detailed instructions.

Citation

• Luis A. Leiva, Morteza Shiripour, Antti Oulasvirta. Modeling How Different User Groups Perceive Webpage Aesthetics. Universal Access in the Information Society, 2022.

@Article{aesthetics,
  author  = {Luis A. Leiva and Morteza Shiripour and Antti Oulasvirta},
  title   = {Modeling How Different User Groups Perceive Webpage Aesthetics},
  journal = {Universal Access in the Information Society (UAIS)},
  year    = {2022},
}
    

Disclaimer

Our software is free for scientific use (licensed under the MIT license). The software must not be distributed without prior permission of the authors. Please contact us if you are planning to use the software for commercial purposes. The authors are not responsible for any implication derived from the use of this software.