Hatim Dafaalla 1,* , Mohammed Abaker 1 , Abdelzahir Abdelmaboud 2, Mohammed Alghobiri 3, Ahmed Abdelmotlab 3, Nazir Ahmad 1, Hala Eldaw 4 and Aiman Hasabelrsou
الملخص الانجليزي
Requirement elicitation represents one of the most vital phases in information system (IS)
and software development projects. Selecting suitable elicitation techniques is critical for eliciting the
correct specification in various projects. Recent studies have revealed that improper novice practices
in this phase have increased the failure rate in both IS and software development projects. Previous
research has primarily relied on creating procedural systems based on contextual studies of elicitation
properties. In contrast, this paper introduces a deep learning model for selecting suitable requirement
elicitation. An experiment was conducted wherein a collected dataset of 1684 technique selection
attributes were investigate with respect to 14 elicitation techniques. The study adopted seven criteria
to evaluate predictive model performance using confusion matrix accuracy, precision, recall, F1 Score,
and area under the ROC curve (AUC) and loss curve. The model scored prediction accuracy of 82%,
precision score of 0.83, recall score of 0.83, F1 score of 0.82, cross-validation score of 0.82 ( 0.10),
One-vs-One ROC AUC score of 0.74, and One-vs-Rest ROC AUC score of 0.75 for each label. Our
results indicate the model’s high prediction ability. The model provides a robust decision-making
process for delivering correct elicitation techniques and lowering the risk of project failure. The
implications of this study can be used to promote the automatization of the elicitation technique
selection process, thereby enhancing current required elicitation industry practices.
د.أيمن حسب الرسول حسين أحمد | Dr.Aiman HassabElrsoul Hussien Ahmad | 1689