| Download | - View final version: Generalized follow-up WHODAS 2.0 assessment through language models and adaptive clustering ensemble in higher education (PDF, 1002 KiB)
|
|---|
| DOI | Resolve DOI: https://doi.org/10.1145/3733155.3734900 |
|---|
| Author | Search for: Kevadiya, RakshilORCID identifier: https://orcid.org/0009-0009-5494-0632; Search for: Akkasi, AbbasORCID identifier: https://orcid.org/0000-0003-4700-4896; Search for: Fraser, Kathleen C1ORCID identifier: https://orcid.org/0000-0002-0752-6705; Search for: Vukovic, BorisORCID identifier: https://orcid.org/0000-0002-5757-2355; Search for: Gunnell, JessieORCID identifier: https://orcid.org/0009-0002-5749-1886; Search for: Tanguay, SoniaORCID identifier: https://orcid.org/0009-0008-8307-2953; Search for: Komeili, MajidORCID identifier: https://orcid.org/0000-0002-4695-3072 |
|---|
| Affiliation | - National Research Council Canada. Digital Technologies
|
|---|
| Funder | Search for: New Frontiers in Research Fund |
|---|
| Format | Text, Article |
|---|
| Conference | PETRA '25: The PErvasive Technologies Related to Assistive Environments, June 25-27, 2025, Corfu Island Greece |
|---|
| Subject | question clustering; language models; disability assessment; WHODAS 2.0 questionnaire; adaptive clustering ensemble |
|---|
| Abstract | This paper addresses the challenge of automating the process of generating personalized follow-up questions (FQs) for students with disabilities based on their responses to the WHODAS 2.0 questionnaire. Given the diverse nature of FQs generated by disability service providers, our research aims to cluster these questions using advanced language models and ensemble clustering techniques. We utilized three different Sentence-Transformers embedding models (RoBERTa, MiniLM and MPNet) combined with clustering algorithms such as HDBSCAN, K-Means, BIRCH, Spectral Clustering, and Gaussian Mixture Models. Furthermore, an Adaptive Clustering Ensemble (ACE) method was employed to improve clustering performance. The results indicate that the ensemble method achieves greater stability and accuracy in clustering compared to individual models. Our findings demonstrate the potential of using AI to streamline the process of assessing and supporting students with disabilities in postsecondary education settings. |
|---|
| Publication date | 2025-07-17 |
|---|
| Publisher | ACM |
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | aaad5af0-a280-4098-99c2-7719c9c36dce |
|---|
| Record created | 2025-09-18 |
|---|
| Record modified | 2025-09-19 |
|---|
