Deep Learning Model for Selecting Suitable Requirements Elicitation Techniques
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...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/18/9060 |
| _version_ | 1827663736421220352 |
|---|---|
| author | Hatim Dafaalla Mohammed Abaker Abdelzahir Abdelmaboud Mohammed Alghobiri Ahmed Abdelmotlab Nazir Ahmad Hala Eldaw Aiman Hasabelrsoul |
| author_facet | Hatim Dafaalla Mohammed Abaker Abdelzahir Abdelmaboud Mohammed Alghobiri Ahmed Abdelmotlab Nazir Ahmad Hala Eldaw Aiman Hasabelrsoul |
| author_sort | Hatim Dafaalla |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T00:49:46Z |
| format | Article |
| id | doaj.art-2e52e2c88c5347af854ff0f3e4041fb9 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T00:49:46Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-2e52e2c88c5347af854ff0f3e4041fb92023-11-23T14:52:27ZengMDPI AGApplied Sciences2076-34172022-09-011218906010.3390/app12189060Deep Learning Model for Selecting Suitable Requirements Elicitation TechniquesHatim Dafaalla0Mohammed Abaker1Abdelzahir Abdelmaboud2Mohammed Alghobiri3Ahmed Abdelmotlab4Nazir Ahmad5Hala Eldaw6Aiman Hasabelrsoul7Department of Computer Science, Applied College, King Khalid University, Muhayil 61913, Saudi ArabiaDepartment of Computer Science, Applied College, King Khalid University, Muhayil 61913, Saudi ArabiaDepartment of Information System, College of Science and Art, King Khalid University, Muhayel 61913, Saudi ArabiaDepartment of Management Information System, College of Business, King Khalid University, Abha 62529, Saudi ArabiaDepartment of Management Information System, College of Business, King Khalid University, Abha 62529, Saudi ArabiaDepartment of Computer Science, Applied College, King Khalid University, Muhayil 61913, Saudi ArabiaDepartment of Information System, College of Computer Science & Information Systems, Al Jouf University, Sakaka 72388, Saudi ArabiaDepartment of Business Administration, Applied College, King Khalid University, Muhayel 61913, Saudi ArabiaRequirement 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.https://www.mdpi.com/2076-3417/12/18/9060requirement elicitationelicitation technique selectiondeep learningneural network |
| spellingShingle | Hatim Dafaalla Mohammed Abaker Abdelzahir Abdelmaboud Mohammed Alghobiri Ahmed Abdelmotlab Nazir Ahmad Hala Eldaw Aiman Hasabelrsoul Deep Learning Model for Selecting Suitable Requirements Elicitation Techniques Applied Sciences requirement elicitation elicitation technique selection deep learning neural network |
| title | Deep Learning Model for Selecting Suitable Requirements Elicitation Techniques |
| title_full | Deep Learning Model for Selecting Suitable Requirements Elicitation Techniques |
| title_fullStr | Deep Learning Model for Selecting Suitable Requirements Elicitation Techniques |
| title_full_unstemmed | Deep Learning Model for Selecting Suitable Requirements Elicitation Techniques |
| title_short | Deep Learning Model for Selecting Suitable Requirements Elicitation Techniques |
| title_sort | deep learning model for selecting suitable requirements elicitation techniques |
| topic | requirement elicitation elicitation technique selection deep learning neural network |
| url | https://www.mdpi.com/2076-3417/12/18/9060 |
| work_keys_str_mv | AT hatimdafaalla deeplearningmodelforselectingsuitablerequirementselicitationtechniques AT mohammedabaker deeplearningmodelforselectingsuitablerequirementselicitationtechniques AT abdelzahirabdelmaboud deeplearningmodelforselectingsuitablerequirementselicitationtechniques AT mohammedalghobiri deeplearningmodelforselectingsuitablerequirementselicitationtechniques AT ahmedabdelmotlab deeplearningmodelforselectingsuitablerequirementselicitationtechniques AT nazirahmad deeplearningmodelforselectingsuitablerequirementselicitationtechniques AT halaeldaw deeplearningmodelforselectingsuitablerequirementselicitationtechniques AT aimanhasabelrsoul deeplearningmodelforselectingsuitablerequirementselicitationtechniques |