Shulou(Shulou.com)11/24 Report--

An AI learning model has been developed by the University of Central Florida (University of Central Florida,UCF) Virtual Reading Lab (Virtual Readability Lab) and Adobe, which aims to provide personalized font recommendations to enhance personal reading experience and help people read more efficiently. Their research shows that machine learning models can improve reading speed by matching reader features with recommended fonts.

The team is made up of Adobe machine learning engineers and researchers who work with vision scientists, printers, data scientists and UCF readability researchers to study Adobe's machine learning model FontMART.

Adobe is a member of the Reading Alliance (The Readability Consortium), which leads UCF's digital readability research, using personalized typesetting to enhance the reader's reading experience.

Ben D. Sawyer, director of the Reading Alliance and UCF Virtual Reading Lab, said: "imagine a device in the future that can identify human reading habits and customize the reading format to help people read at their best. We look forward to the day when people can pick up their devices and read and receive information in their own way."

Screenshot of the web page | Ref. [1] Sawyer and Adobe scientist Zoya Bylinskii participated in the conception of the research and provided guidance throughout the research process. Tianyuan Cai, a machine learning engineer at Acrobat.com, led the FontMART-related research. The study used the font preference test on the UCF Virtual Reading Lab website (see link at the end of the article) as a base value to evaluate the recommendations provided by FontMART.

The results show that after the FontMART model matches the reader features with specific font features, the recommended fonts can improve the reading speed.

Recommended fonts can improve reading speed | the PixabayFontMART model learned to associate fonts with specific reader features after data training with 252 workers. According to the interview with the printer, the study finally selected eight fonts, including serif (Georgia, Merriweather, Times and Source Serif Pro) and sans serif (Arial, Open Sans, Poppins and Roboto).

The researchers found that the effect of fonts varies from person to person. FontMART will learn to establish a relationship between font features and reader characteristics to predict which fonts are suitable for readers with different font familiarity, self-reported reading speed and age. Among them, the age factor has the greatest influence on the font recommendation.

For example, thicker font strokes are easier to read for people with poor eyesight, and such fonts are beneficial to the reading experience of the elderly.

In the later stage of the model, more research is needed to expand the age range of participants, evaluate the effectiveness of the model for other reading environments like different pages, and expand language and related font features to better adapt to the diversity of readers. Subsequent collaboration and research will help to expand the features of model exploration in order to improve the FontMART model and enhance personal reading experience.

reference

[1] Cai, T.A., Wallace, S.S., Rezvanian, T.S., Dobres, J., Kerr, B.B., Berlow, S.S.,... & Bylinskii, Z. (2022, June). Personalized Font Recommendations: Combining ML and Typographic Guidelines to Optimize Readability. Designing Interactive Systems Conference (pp. 1-25). 10.1145/3532106.3533457

[2] https://www.eurekalert.org/news-releases/961726

Related links

[1] Virtual Reading Lab Link: Virtual Readability Lab

[2] read the Alliance related report: Readability Consortium Forms at UCF to Push Reading Research Boundaries | University of Central Florida News

[3] Font preference testing website: https://readability-test.org/ vrl_preference?vrl_portal_

Research team

First / newsletter author Tianyuan Cai/ Ben D. Sawyer

Author unit

Adobe, Inc. (Adobe, United States)

University of Central Florida (University of Central Florida, United States)

Paper information

Released at the Design Interactive Systems Conference (Designing Interactive Systems Conference)

Release date: June 16, 2022

Paper title Personalized Font Recommendations: Combining ML and Typographic Guidelines to Optimize Readability

(DOI: https://doi.org/10.1145/3532106.3533457)

Artificial intelligence in article field

This article comes from the official account of Wechat: I am a scientist iScientist (ID:IamaScientist), compiler: cod, editor: Jin Xiaoming, typesetting: Yin Ningliu

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.