Design Progress Dashboard: Visualising a Quantitative Divergent/Convergent Pattern of Design Team Progress Through Natural Language Processing

Chiu, Matt; Silva, Arlindo; Lim, Siska

doi:10.1007/978-3-031-20418-0_5

Cited by 3 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, the study focuses on data collection on the weekly design statement written by the individuals in the teams instead of obtaining a singular group writeup. The individual writeups are then processed through an NLP workflow similar to Design Progress Dashboard (Chiu et al, 2022) to convert text to numbers before graph plotting. Instead of a singular process, this paper evaluates two NLP upstream methods to break down text into numerical data which is then fed into the two downstream distance-producing frameworks.…”

Section: Methodsmentioning

confidence: 99%

“…The use of text-based data mining processes in attempt to understand the conversations about projects and to produce summaries through various NLP techniques are widely adopted through various means (Dong et al, 2004;Chiu et al, 2022;Ferguson et al, 2022). Design as a process at its various stage revolves around tons of text documentations such as internal reports, design concepts, discourse transcripts, and technical publication where tools like NLP and AI can be utilized gather insights or predict recommendations (Koh, 2022;Siddharth et al, 2022).…”

Section: Application Of Nlp In a Design Coursementioning

confidence: 99%

“…To minimize impurities on the collected data, Chiu et al has come up with a framework to harvest textual information on a singular design statement from every member of the design team that focuses on the actionable goal at the end of every weekly class as a form of reflection (Chiu et al, 2022). The data collected in this approach are precise and is immediately representative of the intention of each student without a complicated data cleaning process.…”

Section: Application Of Nlp In a Design Coursementioning

confidence: 99%

“…With the collection of this textual data in the form of design statements from individual students periodically, the NLP models are able to pick up keywords and produce quantitative graphs that may represent a sort of path of mental thoughts for each student. The path of thoughts mapped through the capturing of written textual data from the students is often referred to as the divergence/convergence traits (Chiu et al, 2022). It appears in various design thinking frameworks including the 4D Double Diamond Framework (4D Framework) (Camburn et al, 2017;UK Design Council, 2019;Lauff et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

“…One common approach is the use of Latent Semantic Analysis (LSA; Landauer et al, 1998), which captures the frequency of occurrence of particular word throughout the design course and is often paired with the use of Cosine similarity to measure distance between points of capture. On the other hand, a more recent combination developed to visualize project divergence is the use of Word-to-Vector (Word2Vec; Mikolov et al, 2013) which creates a corpus word cloud that allows distances representing divergence to be measured through Euclidean distance (Jones et al, 2010;Chiu et al, 2022). This paper aims to look deeper into these four abovementioned NLP approaches and to evaluate their suitability in producing design process diagrams throughout a design course, before making a recommendation for the future AI-driven learning environments.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Visualizing design project team and individual progress using NLP: a comparison between latent semantic analysis and Word2Vector algorithms

Chiu

Lim

Silva

2023

AIEDAM

Self Cite

View full text Add to dashboard Cite

Design has always been seen as an inherently human activity and hard to automate. It requires a lot of traits that are seldom attributable to machines or algorithms. Consequently, the act of designing is also hard to assess. In particular in an educational context, the assessment of progress of design tasks performed by individuals or teams is difficult, and often only the outcome of the task is assessed or graded. There is a need to better understand, and potentially quantify, design progress. Natural Language Processing (NLP) is one way of doing so. With the advancement in NLP research, some of its models are adopted into the field of design to quantify a design class performance. To quantify and visualize design progress, the NLP models are often deployed to analyze written documentation collected from the class participants at fixed time intervals through the span of a course. This paper will explore several ways of using NLP in assessing design progress, analyze its advantages and shortcomings, and present a case study to demonstrate its application. The paper concludes with some guidelines and recommendations for future development.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Application Of Nlp In a Design Coursementioning

confidence: 99%

Section: Application Of Nlp In a Design Coursementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Visualizing design project team and individual progress using NLP: a comparison between latent semantic analysis and Word2Vector algorithms

Chiu

Lim

Silva

2023

AIEDAM

Self Cite

View full text Add to dashboard Cite

show abstract

Automating Useful Representations of the Design Process from Design Protocols

Kelly,

Greentree,

Sosa

et al. 2024

Design Computing and Cognition’24

View full text Add to dashboard Cite

Using AI-Enabled Divergence and Convergence Patterns as a Quantitative Artifact in Design Education

Chiu,

Sim,

Mun

et al. 2024

Journal of Mechanical Design

View full text Add to dashboard Cite

Design education has traditionally relied heavily on physical integration as it involves a lot of hands-on work, group critiques, and collaborative projects, but the COVID-19 pandemic has forced many institutions to adapt to remote teaching and learning environments. This has created challenges for design educators who have had to find ways to evaluate students' progress in the absence of in-person interactions. In this paper, we are proposing a dashboard visualisation approach that helps educators to monitor the progression of the entire class of students using Artificial Intelligence (AI) by tracking a time-based evolution of a design statement. This approach uses various Natural Language Processing (NLP) models to produce stock-like charts which represent students' and student groups' progression through a series of divergence and convergence phases. These charts become a form of Design Artifact that allows educator(s) to gain a birds-eye view of the class and react to groups that may require assistance; at the same time it becomes a qualitative means of evaluation and comparison across students and groups. Towards the end, this paper also showcases a web-based platform that is publicly available using such methodology, a case study that applied so methodology and recommendation of future works possible.

show abstract

Design Progress Dashboard: Visualising a Quantitative Divergent/Convergent Pattern of Design Team Progress Through Natural Language Processing

Cited by 3 publications

References 28 publications

Visualizing design project team and individual progress using NLP: a comparison between latent semantic analysis and Word2Vector algorithms

Visualizing design project team and individual progress using NLP: a comparison between latent semantic analysis and Word2Vector algorithms

Automating Useful Representations of the Design Process from Design Protocols

Using AI-Enabled Divergence and Convergence Patterns as a Quantitative Artifact in Design Education

Contact Info

Product

Resources

About