Visual Blending for Concept Representation: A Case Study on Emoji Generation
- PDF / 2,283,352 Bytes
- 33 Pages / 439.37 x 666.142 pts Page_size
- 98 Downloads / 134 Views
Visual Blending for Concept Representation: A Case Study on Emoji Generation João M. Cunha1 · Nuno Lourenço1 · Pedro Martins1 · Penousal Machado1 Received: 19 January 2020 / Accepted: 4 September 2020 © Ohmsha, Ltd. and Springer Japan KK, part of Springer Nature 2020
Abstract The emoji connection between visual representation and semantic knowledge, together with its large conceptual coverage have the potential to be exploited in computational approaches to the visual representation of concepts. An example of a system that explores this potential is Emojinating—a system that uses a process of visual blending of existing emoji to represent concepts. In this paper, we use the Emojinating system as a case study to analyse the appropriateness of visual blending for the visual representation of concepts. We conduct three experiments in which we analyse output quality, type of blend used, usefulness to the user and ease of interpretation. Our main contributions are the following: (i) the production of a doubleword concept list for testing the system; (ii) an extensive user study using two different concept lists (single-word and double-word); and (iii) a study that compares produced blends with user drawings. Keywords Computational creativity · Visual blending · Emoji · Computational design · Concept representation · Computational generation This work is partially funded by national funds through the FCT - Foundation for Science and Technology, I.P., within the scope of the project CISUC - UID/CEC/00326/2020 and by European Social Fund, through the Regional Operational ProgramCentro 2020, and under the grant SFRH/BD/120905/2016. This work includes data from ConceptNet 5, which was compiled by the Commonsense Computing Initiative and is freely available under the Creative Commons Attribution-ShareAlike license (CC BY SA 4.0) from conceptnet.io. * João M. Cunha [email protected] Nuno Lourenço [email protected] Pedro Martins [email protected] Penousal Machado [email protected] 1
Department of Informatics Engineering, Centre for Informatics and Systems of the University of Coimbra, Coimbra, Portugal
123
Vol.:(0123456789)
New Generation Computing
Introduction Visual blending consists in the production of new visual representations (e.g. images) by merging at least two existing ones. In Computational Creativity research, it can be combined with computational approaches to Conceptual Blending [22] to produce representations for a blended mental space (e.g. [32]), which can lead to what is referred to as Visual Conceptual Blending [15]. When considering research on visual blending, it is possible to observe the pursuit of a system that is able to turn concepts into visual representations. Confalonieri et al. [9] propose argumentation as a way to evaluate and refine the quality of blended computer icons. Xiao and Linkola [45] present a semi-automatic system to produce visual compositions for specific meanings (e.g. Electricity is green). Ha and Eck [24] train a recurrent neural network that generalises concepts and
Data Loading...
