Nd
N. de Wekker
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
1 records found
1
A Framework-Based Tool for Designers
A Classification of Healthcare Sound Interventions
This graduation project explored how the TWAF framework could be translated into a more practical and accessible tool for analysing sound-driven design projects in healthcare. TWAF describes four ways in which sound can function in design, but applying the framework consistently can be difficult for first-time users due to its abstract and interpretive nature.
The project began with the development of a Manual Archiving Method to better understand how TWAF could be operationalised. Through this process, several challenges became visible, including difficulties in distinguishing between TWAF modes and the need for clearer guidance and examples.
Based on these findings, the project shifted towards the development of a Guided TWAF Interpretation Tool. Instead of fully automating TWAF classification, the prototype combined lexicon-based analysis, semantic similarity techniques, and visual evidence representations to support reflection and interpretation. The system presented TWAF ratings together with indicator words, concordances, and sentence-level evidence to help users explore how sound functions within healthcare design projects.
The evaluation showed that participants developed a better understanding of the role of sound in the projects. Participants also critically reflected on the generated outputs rather than blindly accepting them, highlighting the importance of transparency and human interpretation within computational analysis systems.
Overall, the project demonstrates the potential of combining computational analysis with human interpretation to support sound-driven design exploration and education. The findings suggest that AI may be most valuable as a reflective support tool rather than as a fully automated classification system within the context of TWAF. ...
The project began with the development of a Manual Archiving Method to better understand how TWAF could be operationalised. Through this process, several challenges became visible, including difficulties in distinguishing between TWAF modes and the need for clearer guidance and examples.
Based on these findings, the project shifted towards the development of a Guided TWAF Interpretation Tool. Instead of fully automating TWAF classification, the prototype combined lexicon-based analysis, semantic similarity techniques, and visual evidence representations to support reflection and interpretation. The system presented TWAF ratings together with indicator words, concordances, and sentence-level evidence to help users explore how sound functions within healthcare design projects.
The evaluation showed that participants developed a better understanding of the role of sound in the projects. Participants also critically reflected on the generated outputs rather than blindly accepting them, highlighting the importance of transparency and human interpretation within computational analysis systems.
Overall, the project demonstrates the potential of combining computational analysis with human interpretation to support sound-driven design exploration and education. The findings suggest that AI may be most valuable as a reflective support tool rather than as a fully automated classification system within the context of TWAF. ...
This graduation project explored how the TWAF framework could be translated into a more practical and accessible tool for analysing sound-driven design projects in healthcare. TWAF describes four ways in which sound can function in design, but applying the framework consistently can be difficult for first-time users due to its abstract and interpretive nature.
The project began with the development of a Manual Archiving Method to better understand how TWAF could be operationalised. Through this process, several challenges became visible, including difficulties in distinguishing between TWAF modes and the need for clearer guidance and examples.
Based on these findings, the project shifted towards the development of a Guided TWAF Interpretation Tool. Instead of fully automating TWAF classification, the prototype combined lexicon-based analysis, semantic similarity techniques, and visual evidence representations to support reflection and interpretation. The system presented TWAF ratings together with indicator words, concordances, and sentence-level evidence to help users explore how sound functions within healthcare design projects.
The evaluation showed that participants developed a better understanding of the role of sound in the projects. Participants also critically reflected on the generated outputs rather than blindly accepting them, highlighting the importance of transparency and human interpretation within computational analysis systems.
Overall, the project demonstrates the potential of combining computational analysis with human interpretation to support sound-driven design exploration and education. The findings suggest that AI may be most valuable as a reflective support tool rather than as a fully automated classification system within the context of TWAF.
The project began with the development of a Manual Archiving Method to better understand how TWAF could be operationalised. Through this process, several challenges became visible, including difficulties in distinguishing between TWAF modes and the need for clearer guidance and examples.
Based on these findings, the project shifted towards the development of a Guided TWAF Interpretation Tool. Instead of fully automating TWAF classification, the prototype combined lexicon-based analysis, semantic similarity techniques, and visual evidence representations to support reflection and interpretation. The system presented TWAF ratings together with indicator words, concordances, and sentence-level evidence to help users explore how sound functions within healthcare design projects.
The evaluation showed that participants developed a better understanding of the role of sound in the projects. Participants also critically reflected on the generated outputs rather than blindly accepting them, highlighting the importance of transparency and human interpretation within computational analysis systems.
Overall, the project demonstrates the potential of combining computational analysis with human interpretation to support sound-driven design exploration and education. The findings suggest that AI may be most valuable as a reflective support tool rather than as a fully automated classification system within the context of TWAF.