Semantics-aware typographical choices via affective associations

Abstract

The task of selecting suitable fonts for a given text is non-trivial, as tens of thousands of fonts are available, and the choice of font has been shown to affect the perception of the text as well as of the author or of the brand being advertized. Aiming to support the development of font recommendation tools, we create a typographical lexicon providing associations between words and fonts. We achieve this by means of affective evocations, making use of font-emotion and word-emotion relationships. For this purpose, we first determine font vectors for a set of ten emotion attributes, based on word similarities and antonymy information. We evaluate these associations through a user study via Mechanical Turk, which, for eight of the ten emotions, shows a strong user preference towards the fonts that are found to be congruent by our predicted data. Subsequently, this data is used to calculate font vectors for specific words, by relying on the emotion associations of a given word. This leads to a set of font associations for 6.4K words. We again evaluate the resulting dataset using Mechanical Turk, on 25 randomly sampled words. For the majority of these words, the responses indicate that fonts with strong associations are preferred, and for all except 2 words, fonts with weak associations are dispreferred. Finally, we further extend the dataset using synonyms of font attributes and emotion names. The resulting FontLex resource provides mappings between 6.7K words and 200 fonts.

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

“…THERIF: A Pipeline for Generating Themes for Readability with Iterative Feedback existing reading studies often focus on objective measures such as reading comprehension and speed (Cai et al, 2022;Chatrangsan and Petrie, 2019;Zhu et al, 2021;McKoon and Ratcliff, 2016). However, factors such as comfort and personal preference are equally important to readers when reading digitally, although consistent criteria may not always exist (Zhu et al, 2021;Bernard et al, 2003;Kulahcioglu and de Melo, 2020). Recommending text settings while balancing multiple objectives and meeting diverse readers' preferences is a challenging problem, which may explain why there is limited work beyond personalized font recommendation (Cai et al, 2022).…”

Personality Predictive Lexical Cues and Their Correlations

“…Lexical Analyses. Lexicon-driven analyses have proven fruitful in areas such as sentiment analysis (Ding et al, 2008;Mohammad et al, 2013;Kiritchenko et al, 2014;Islam et al, 2020) and emotion analysis (Kulahcioglu and de Melo, 2018;Raji and de Melo, 2020;Raji and de Melo, 2021), especially when there is no labeled data, as well as in social science and digital humanities (Pennebaker et al, 2001). With this approach, a dictionary of words (or bag of words) is generated, with a positive or negative value assigned to each word, reflecting the predictive power or correlation strength between the word and the specific target label or variable.…”

Let Me Choose: From Verbal Context to Font Selection

“…They support the idea of typefaces consistently perceived to have particular personas, emotions, or tones. More recently, FontLex (Kulahcioglu and De Melo, 2018) was the first to find the association between fonts and words by utilizing font-emotion and word-emotion relationships. Instead of focusing on independent words, our proposed model suggests fonts by considering the broader context of the whole text.…”