Implementing and Evaluating a Font Recommendation System Through Emotion-Based Content-Font Mapping

Author:

Lim Soon-Bum1,Ji Young-Seo1ORCID,Ahn Byunghak2,Park Jae Hong3,Song Yoojeong4ORCID

Affiliation:

1. Department of IT Engineering, Research Institute of ICT Convergence, Sookmyung Women’s University, Seoul 04310, Republic of Korea

2. Visual Communication Design, School of Design, Hongik University, Seoul 04066, Republic of Korea

3. Department of Visual Arts, Mokpo National University, Muan-gun 58554, Republic of Korea

4. School of Computer Science, Semyung University, Jecheon 27136, Republic of Korea

Abstract

Rapid digital content growth demands pivotal font selection for design and communication. Our study focuses on a font recommendation system that aligns fonts with content emotions. To achieve this, we define font-emotions and quantify them. Additionally, we leverage deep learning techniques for content analysis. Understanding common emotional perceptions, we aimed to align fonts with content emotions. After evaluating diverse mapping methods, we determined a correlation analysis-based model to be most effective. Implementing this model, we verified its utility through usability evaluations. Our proposed system not only assists users with limited design knowledge in receiving contextually fitting font suggestions but also extends its application across various digital content realms.

Funder

National Research Foundation of Korea

Publisher

MDPI AG

Reference28 articles.

1. Font matters: Understanding typeface selection by political campaigns;Haenschen;Int. J. Commun.,2021

2. Fundamentals of graphic design—Essential tools for effective visual science communication;Murchie;Facets,2020

3. Ueki, R., Yokoyama, K., and Nakamura, S. (2023). International Conference on Human-Computer Interaction, Springer Nature.

4. Modeling fonts in context: Font prediction on web designs;Zhao;Comput. Graph. Forum,2018

5. Tsuji, K., Uchida, S., and Iwana, B.K. (2021). Document Analysis and Recognition–ICDAR 2021 Workshops: Lausanne, Switzerland, September 5–10, 2021, Proceedings, Part II 16, Springer International Publishing.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3