THERIF: A Framework for Generating Themes for Readability with Iterative Feedback

Digital reading applications give readers the ability to customize fonts, sizes, and spacings, all of which have been shown to improve various aspects of reading, including reading comfort, comprehension, and speed. However, tweaking these text features can be challenging, especially given their interactions on the final look and feel of the text. Our solution is to offer readers preset combinations of font, character, word and line spacing, which we bundle together into reading themes. To arrive at a recommended set of reading themes, we present our THERIF framework, which combines crowdsourced text adjustments, ML-driven clustering of text formats, and design sessions. We show that after four iterations of our framework, we converge on a set of three COR themes (Compact, Open, and Relaxed) that match diverse readers' needs, when evaluating the reading speeds, comprehension scores, and preferences of hundreds of readers with and without dyslexia, using crowdsourced experiments.

Paper

Full paper
Late-breaking work

Final Themes

Final Themes

Study Prototypes
Pilot Study

Find text settings that matter

In pilot study, participants had access to a wide range of controls for tailoring reading interfaces to their preference.

Crowdworkers

Rate and refine

In the main study, participants review themes from the previous iteration and select one to fine-tune further.

Designers

Refine and supplement

Designers use the Participant Prototype to review the themes and use the Designer Prototype to create supplementary reading themes.

Reading Effectiveness

Speed, comprehension, comfort

A separate group of participants read in all final reading themes and a control theme, their speed, comprehension, and comfort ratings recorded.