| Presentation | 2021-03-06 Software Bug Severity Prediction with BERT Tomoki Yamada, Takako Nakatani, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper aims to automatically assess the severity of software bug reports issued from a large-scale enterprise system construction using BERT. Automatic assessment of bug severity improves the quality of software as well as reduces the cost of development. The targeted bug reports are relatively small (around 10000) and written in Japanese, though the major preceding studies conducted the similar classification on the massive sets (>100000) of bug reports in English from open source software. In addition, unlike preceding studies that commonly used meta-data of bugs as explanatory variables, the proposed classification model is simply based on the bug description text. The result shows that the accuracy of the BERT-based model is as high as the preceding studies, though the size of data is far smaller. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | BERT / Bug Triage / Severity Prediction / Software Development / arge-scale Enterprise System / L |
| Paper # | KBSE2020-47 |
| Date of Issue | 2021-02-26 (KBSE) |
| Conference Information | |
| Committee | KBSE |
|---|---|
| Conference Date | 2021/3/5(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Hiroyuki Nakagawa(Osaka Univ.) |
| Vice Chair | Takuya Saruwatari(NTT Data) |
| Secretary | Takuya Saruwatari(OKI) |
| Assistant | Shinpei Ogata(Shinshu Univ.) / Erina Nakihara(Doshisha Univ,) |
| Paper Information | |
| Registration To | Technical Committee on Knowledge-Based Software Engineering |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Software Bug Severity Prediction with BERT |
| Sub Title (in English) | Case Study on a Large-scale Enterprise System |
| Keyword(1) | BERT |
| Keyword(2) | Bug Triage |
| Keyword(3) | Severity Prediction |
| Keyword(4) | Software Development |
| Keyword(5) | arge-scale Enterprise System |
| Keyword(6) | L |
| 1st Author's Name | Tomoki Yamada |
| 1st Author's Affiliation | Open University of Japan(OUJ) |
| 2nd Author's Name | Takako Nakatani |
| 2nd Author's Affiliation | Open University of Japan(OUJ) |
| Date | 2021-03-06 |
| Paper # | KBSE2020-47 |
| Volume (vol) | vol.120 |
| Number (no) | KBSE-423 |
| Page | pp.pp.77-82(KBSE), |
| #Pages | 6 |
| Date of Issue | 2021-02-26 (KBSE) |