A carregar...
Projeto de investigação
Creativity Support Tools for Sustainability: from divergent to convergent thinking
Financiador
Autores
Publicações
Creativity support tool for sustainability: an LLM-Assisted Creative Process
Publication . Rodrigues, Ana Isabel Mendonça; Rodrigues, Ana Isabel; Campos, Pedro Filipe Pereira; Cabral, Diogo Nuno Crespo Ribeiro
Promoting new ideas is fundamental and promising for fostering innovation in various sectors.
Creativity is the fundamental basis of innovation, serving as a springboard for the development
of new and useful ideas in their application context, driving innovation in various spheres of
society, from organizational processes to cultural transformations. Driven by the impact and
evolution of Human-Computer Interaction (HCI) and the rise of the creative process through
technology, this doctoral thesis focuses on user experience (UX) during the creative process
through the development of a creativity support tool - System Approach to Idea Evaluation and
Selection of Ecosystem (SAIESE) - based on a Large Language Model (LLM).
The central question of this thesis is to analyze which functionalities can be implemented in
creativity support tools, with the aim of increasing support for the creative process (i.e.,
generation, evaluation, and selection of ideas) and, consequently, improving the creative
experience during the resolution of sustainable tasks or problems. In this context, the creative
process was guided by three sustainability metrics (i.e., environmental impact, economic
benefits, and social effects), ensuring that creativity and the process were directed to the
application context of this research.
The methodology adopted combines a hybrid research approach (qualitative and quantitative
data) and a systematic literature review (2012-2025), which established the theoretical basis for
the practical development of the prototype.
The prototypes developed were accompanied by empirical validations guided by the research
questions initially defined and by some research hypotheses. After extensive evaluations,
SAIESE proved to be a successful example of a creativity support tool based on a large-scale
language model, providing efficient and effective support throughout the creative process.
The research concludes with the development of a conceptual approach that synthesizes the
different dimensions of the research. We present the theoretical framework (Divergent
Convergent Thinking Framework (DCTF)) that represents the spatialization of the creative
process through the Ideas Space and Solution Space present in the Double Diamond Model.
Next, we revisit the classic principles of CSTs in light of contemporary LLM-based
technologies. Finally, we explore the dynamics of control, transparency, and trust in human-AI collaboration, particularly in the context of convergent thinking and AI-assisted decision
making.
In conclusion, this thesis proposes a new creativity support tool that combines human
cognitive processes with the capabilities of an LLM to inspire future researchers, such as
designers, who want to develop tools tailored to application contexts.
Exploring the creative process in a brainstorming session to develop a web-based system for idea selection
Publication . Rodrigues, Ana; Honório, David; Cabral, Diogo; Campos, Pedro F.; Pereira Campos, Pedro Filipe
Betting on new and promising ideas is fundamental for innovation
in various sectors, helping the world that faces so many adversi
ties. To increase these ideas, the stages of evaluation and selection
of ideas in the creative processes need to be improved and not
neglected. To minimize this problem and contribute to the scien
tific advance in the creativity-oriented HCI, we present a tool for
selecting ideas used after brainstorming sessions. Our prototype
is inspired by the conclusions of an observational study that we
conducted with six students in a classroom, in which the students’
objective was to plan the making of a video for a social institution
that helps the neediest people.
Creativity support tools and convergent thinking: a preliminary review on idea evaluation and selection
Publication . Rodrigues, Ana; Cabral, Diogo; Campos, Pedro F.; Pereira Campos, Pedro Filipe; Campos, Pedro
Creativity Support Tools (CSTs) have grown exponentially in the
HCI field. However, this growth has always leaned towards diver
gent thinking, thus neglecting convergentthinking. Weconfirmthis
information based on a preliminary review between 2012 and 2022
in the ACM Digital Library. Our findings confirm that researchers
and practitioners have been primarily interested in developing tools
to support idea generation, minimizing studies on evaluating and
selecting ideas. We focused our research on four major points: i) the
domain of the tool, ii) the type of system and interface developed in
the tools, iii) the methodology used, and iv) the creative context of
Pedro Campos
ITI/LARSyS and WowSystems, Lda.,
University of Madeira
pedro.campos@iti.larsys.pt
the tools. Based on this information, we contribute six guidelines
to support the improvement of existing CSTs and the development
of new CSTs.
Inside the solution diamond: the role of CSTs supporting divergent and convergent thinking
Publication . Rodrigues, Ana; Cabral, Diogo; Campos, Pedro; Rodrigues, Ana Isabel; Pereira Campos, Pedro Filipe; Campos, Pedro
Inspired by the growing development of Creativity Support Tools
(CSTs) to enhance creative work over the past ten years, we in
vestigate the evolution of these tools in supporting divergent and
convergent thinking based on the Double Diamond model. How
ever, the approaches developed so far do not represent the complete
design space, indicating the existence of a limitation during the
creative process. This article presents the Divergent-Convergent
Thinking Framework (DCTF) to support an understanding of the
composition of the creative spectrum. Based on a literature review
(N=96), our framework synthesizes key categories of creativity and,
particularly, research on CSTs. We propose six dimensions and
four challenges and opportunities to guide the analysis of already
developed CSTs, the development of future CSTs, and how to inte
grate them into users’ workflow. To test its relevance, we present a
possible scenario for the framework’s applicability in the context
of sustainable design-oriented creativity. We demonstrate how the
framework guides the selection of ideas, supporting the cyclical
transition between divergent and convergent thinking.
LLMs-Assisted decision-making in sustainable contexts
Publication . Rodrigues, Ana; Cabral, Diogo; Campos, Pedro; Rodrigues, Ana Isabel; Pereira Campos, Pedro Filipe; Campos, Pedro
Promoting sustainability through creative approaches offers a path
way to achieving sustainability goals, yet the resulting solutions
often lack efficiency and effectiveness. Addressing this challenge,
we introduce SAIESE, a Creativity Support Tool (CST) leveraging
a Large Language Model (LLM) to support the creative process,
the generation, evaluation, and selection of sustainable ideas. Our
work articulates LLMs role in exploration and selection, focusing
on sustainable ideas based on three metrics- Environmental Impact,
Economic Benefits, and Social Effects. Our evaluation demonstrates
that the prototype outperforms human evaluative tasks in usability,
creative thinking, and decision-making while reducing cognitive
workload. However, its effectiveness in promoting creativity de
pends on the clarity of ideas, underlining the importance of hu
man collaboration in ambiguous contexts. This work articulates
the potential of AI in creativity, expanding current research on
CSTs by highlighting sustainability-oriented creative processes and
decision-making support.
Unidades organizacionais
Descrição
Palavras-chave
, Exact sciences ,Exact sciences/Computer and information sciences
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia, I.P.
Programa de financiamento
Número da atribuição
2021.06734.BD