Understanding How Large Language Models Can Assist Designers in Ideating User-centered Solutions

No Thumbnail Available
Files
Toimela_Annina_2024.pdf (298.64 KB)
Journal Title
Journal ISSN
Volume Title
Sähkötekniikan korkeakoulu | Bachelor's thesis
Electronic archive copy is available locally at the Harald Herlin Learning Centre. The staff of Aalto University has access to the electronic bachelor's theses by logging into Aaltodoc with their personal Aalto user ID. Read more about the availability of the bachelor's theses.
Date
2024-05-26
Department
Major/Subject
Informaatioteknologia
Mcode
ELEC3015
Degree programme
Sähkötekniikan kandidaattiohjelma
Language
fi
Pages
37
Series
Abstract
A solution to the challenges faced by designers during the user-centered design (UCD) process are large language models (LLMs). The aim of this bachelor’s thesis is to explore how LLMs can assist designers in creating user-centered design solutions. This bachelor’s thesis is a literature review that uses research and literature related to LLMs, UCD and the ways in which they connect. LLMs are artificial intelligence (AI)-based models that perform natural language processing (NLP) tasks. Based on the results of the literature review, it can be concluded that it is possible to use LLMs to assist designers with ideating UCD solutions. LLMs assist designers particularly well during time restrictions and design fixation. Ideating with the assistance of LLMs saves designers time and provides them with new design ideas when lacking inspiration. LLMs can also be given prompts that make them generate design solutions that meet the needs of various user groups. Despite their capabilities, LLMs are unable to solve all of the challenges designers face during the ideation process. Research shows that many designers practicing UCD are hesitant about using AI as a tool, fearing of disintegrating their creativity in the process. Despite these findings, LLMs have significant potential in helping designers create user-centered solutions. Future research into developing LLMs specifically to assist designers will further these ambitions.
Description
Supervisor
Aalto, Samuli
Thesis advisor
Joongi, Shin
Keywords
UCD, LLM, NLP, HCI
Other note
Citation