Story Point Estimation Using Issue Reports With Deep Attention Neural Network
Background: Estimating the effort required for software engineering tasks is incredibly tricky, but it is critical for project planning. Issue reports are frequently used in the agile community to describe tasks, and story points are used to estimate task effort. Aim: This paper proposes a machine...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wroclaw University of Science and Technology
2023-04-01
|
| Series: | e-Informatica Software Engineering Journal |
| Subjects: | |
| Online Access: | https://www.e-informatyka.pl/index.php/einformatica/volumes/volume-2023/issue-1/article-4/ |
| _version_ | 1797942515721043968 |
|---|---|
| author | Haithem Kassem Khaled Mahar Amani A. Saad |
| author_facet | Haithem Kassem Khaled Mahar Amani A. Saad |
| author_sort | Haithem Kassem |
| collection | DOAJ |
| description | Background: Estimating the effort required for software engineering tasks is incredibly tricky, but it is critical for project planning. Issue reports are frequently used in the agile community to describe tasks, and story points are used to estimate task effort.
Aim: This paper proposes a machine learning regression model for estimating the number of story points needed to solve a task. The system can be trained from raw input data to predict outcomes without the need for manual feature engineering.
Method: Hierarchical attention networks are used in the proposed model. It has two levels of attention mechanisms implemented at word and sentence levels. The model gradually constructs a document vector by grouping significant words into sentence vectors and then merging significant sentence vectors to create document vectors. Then, the document vectors are fed into a shallow neural network to predict the story point.
Results: The experiments show that the proposed approach outperforms the state-of-the-art technique Deep-S which uses Recurrent Highway Networks. The proposed model has improved Mean Absolute Error (MAE) by an average of 16.6% and has improved Median Absolute Error (MdAE) by an average of 53%.
Conclusion: An empirical evaluation shows that the proposed approach outperforms the previous work. |
| first_indexed | 2024-04-10T20:09:46Z |
| format | Article |
| id | doaj.art-06839df155df4a33b19ff7f367f7171f |
| institution | Directory Open Access Journal |
| issn | 1897-7979 2084-4840 |
| language | English |
| last_indexed | 2024-04-10T20:09:46Z |
| publishDate | 2023-04-01 |
| publisher | Wroclaw University of Science and Technology |
| record_format | Article |
| series | e-Informatica Software Engineering Journal |
| spelling | doaj.art-06839df155df4a33b19ff7f367f7171f2023-01-26T14:06:09ZengWroclaw University of Science and Technologye-Informatica Software Engineering Journal1897-79792084-48402023-04-0117110.37190/e-Inf230104Story Point Estimation Using Issue Reports With Deep Attention Neural NetworkHaithem KassemKhaled MaharAmani A. Saad Background: Estimating the effort required for software engineering tasks is incredibly tricky, but it is critical for project planning. Issue reports are frequently used in the agile community to describe tasks, and story points are used to estimate task effort. Aim: This paper proposes a machine learning regression model for estimating the number of story points needed to solve a task. The system can be trained from raw input data to predict outcomes without the need for manual feature engineering. Method: Hierarchical attention networks are used in the proposed model. It has two levels of attention mechanisms implemented at word and sentence levels. The model gradually constructs a document vector by grouping significant words into sentence vectors and then merging significant sentence vectors to create document vectors. Then, the document vectors are fed into a shallow neural network to predict the story point. Results: The experiments show that the proposed approach outperforms the state-of-the-art technique Deep-S which uses Recurrent Highway Networks. The proposed model has improved Mean Absolute Error (MAE) by an average of 16.6% and has improved Median Absolute Error (MdAE) by an average of 53%. Conclusion: An empirical evaluation shows that the proposed approach outperforms the previous work. https://www.e-informatyka.pl/index.php/einformatica/volumes/volume-2023/issue-1/article-4/story pointsdeep learningglovehierarchical attention networksagileplanning poker |
| spellingShingle | Haithem Kassem Khaled Mahar Amani A. Saad Story Point Estimation Using Issue Reports With Deep Attention Neural Network e-Informatica Software Engineering Journal story points deep learning glove hierarchical attention networks agile planning poker |
| title | Story Point Estimation Using Issue Reports With Deep Attention Neural Network |
| title_full | Story Point Estimation Using Issue Reports With Deep Attention Neural Network |
| title_fullStr | Story Point Estimation Using Issue Reports With Deep Attention Neural Network |
| title_full_unstemmed | Story Point Estimation Using Issue Reports With Deep Attention Neural Network |
| title_short | Story Point Estimation Using Issue Reports With Deep Attention Neural Network |
| title_sort | story point estimation using issue reports with deep attention neural network |
| topic | story points deep learning glove hierarchical attention networks agile planning poker |
| url | https://www.e-informatyka.pl/index.php/einformatica/volumes/volume-2023/issue-1/article-4/ |
| work_keys_str_mv | AT haithemkassem storypointestimationusingissuereportswithdeepattentionneuralnetwork AT khaledmahar storypointestimationusingissuereportswithdeepattentionneuralnetwork AT amaniasaad storypointestimationusingissuereportswithdeepattentionneuralnetwork |