DistilBERT for User Story Quality Assessment
Collection
Resources for Fine-Tuned DistilBERT for Automated User Story Quality Assessment, including eight DistilBERT models and a refined QUS dataset. • 9 items • Updated
Model Description
This repository contains a fine-tuned DistilBERT model for the automated assessment of the Well Formed criterion of the Quality User Story (QUS) framework.
The model performs binary text classification to determine whether a user story contains the structural components required by the user-story format.
Under QUS, a well-formed user story must include at least a role identifying the stakeholder or user perspective and a means describing the requested functionality. The rationale or ends component is optional.
The model was developed as part of the study "Fine-Tuned DistilBERT for Automated User Story Quality Assessment".
Classification task
- Input: A user story written in natural language.
- Output: Binary classification indicating compliance with the Well Formed criterion.
- Correct: The story contains at least an identifiable role and requested functionality.
- Incorrect: The story lacks one or more of the structural components required to constitute a user story.
This model is one of eight criterion-specific DistilBERT models developed for the individual quality criteria of the QUS framework.
- Downloads last month
- 19
Model tree for devleoespinosa/DistilBERT-AUSQ-SL-Well-Formed
Base model
distilbert/distilbert-base-uncased