| Presentation | 2022-03-08 Multiple Feature Analysis for Problem Recommendation in Online Judge System Noah Sembu, Erina Makihara, Ryota Shinhama, Keiko Ono, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The Online Judge System (OJS) contains a wide variety of problems, and it is difficult for users to select an optimum problem for their own level of programming understanding. Therefore, we aim to support self-study by focusing on users' submitted histories in OJS and recommending problems that match learners' learning stages. In our previous study, we have developed a problem transition model by learning the submitted history and corresponding result using Long Short-Term Memory (LSTM) which is one of the deep learning model. However, it is not possible to recommend problems which is newly added to OJS. In this study, we examine the effectiveness of problem difficulty and tags as new features for problem recommendation. We used LSTM to develop the model using submitted history, which is time-series data, and evaluated it. We developed problem recommendation models in the classification and regression models, and confirmed the effectiveness of the classification and regression models. The result indicates that the classification model is effective for the problem recommendation model, and the problem difficulty and the problem tags are considered to be effective for problem recommendation model. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Programming / Online Judge System / Self study / Long Short-Term Memory |
| Paper # | SS2021-64 |
| Date of Issue | 2022-02-28 (SS) |
| Conference Information | |
| Committee | SS |
|---|---|
| Conference Date | 2022/3/7(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Software Science etc. |
| Chair | Takashi Kobayashi(Tokyo Inst. of Tech.) |
| Vice Chair | Kozo Okano(Shinshu Univ.) |
| Secretary | Kozo Okano(Hiroshima City Univ.) |
| Assistant | Shinpei Ogata(Shinshu Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Software Science |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Multiple Feature Analysis for Problem Recommendation in Online Judge System |
| Sub Title (in English) | |
| Keyword(1) | Programming |
| Keyword(2) | Online Judge System |
| Keyword(3) | Self study |
| Keyword(4) | Long Short-Term Memory |
| 1st Author's Name | Noah Sembu |
| 1st Author's Affiliation | Doshisha University(Doshisha Univ.) |
| 2nd Author's Name | Erina Makihara |
| 2nd Author's Affiliation | Doshisha University(Doshisha Univ.) |
| 3rd Author's Name | Ryota Shinhama |
| 3rd Author's Affiliation | Doshisha University(Doshisha Univ.) |
| 4th Author's Name | Keiko Ono |
| 4th Author's Affiliation | Doshisha University(Doshisha Univ.) |
| Date | 2022-03-08 |
| Paper # | SS2021-64 |
| Volume (vol) | vol.121 |
| Number (no) | SS-416 |
| Page | pp.pp.133-138(SS), |
| #Pages | 6 |
| Date of Issue | 2022-02-28 (SS) |