Presentation | 2004-10-18 A Java Class File Recommender System Based on Collaborative Filtering Takeshi KAKIMOTO, Masateru TSUNODA, Naoki OHSUGI, Akito MONDEN, Ken'ichi MATSUMOTO, |
---|---|
PDF Download Page | ![]() |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Today, most software development platforms provide various software components. However, some software developers are not aware of useful components because extremely large amount of components are provided. This paper propose a system recommending the developers some Java class files by using Collaborative Filtering. Once a developer venters a Java class file which has been developed in ongoing project, the proposed system investigates used Java classes in the entered class file. Next, the system finds some similar class files from already completed class files which made in the past projects. Next, the system recommends the developer some Java classes used in the similar class files and not used in the entered Java class files. We experimentally evaluated recommendation accuracy of the proposed system with four criteria (recall, precision, F1-value, Half-life Utility). The results shows the proposed system outperformed quadruply the simple method recommending the most frequently used Java classes. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | information filtering / similarity / similarity computation / refactoring / J2SE |
Paper # | DE2004-111,DC2004-26 |
Date of Issue |
Conference Information | |
Committee | DE |
---|---|
Conference Date | 2004/10/11(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Data Engineering (DE) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Java Class File Recommender System Based on Collaborative Filtering |
Sub Title (in English) | |
Keyword(1) | information filtering |
Keyword(2) | similarity |
Keyword(3) | similarity computation |
Keyword(4) | refactoring |
Keyword(5) | J2SE |
1st Author's Name | Takeshi KAKIMOTO |
1st Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology() |
2nd Author's Name | Masateru TSUNODA |
2nd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
3rd Author's Name | Naoki OHSUGI |
3rd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
4th Author's Name | Akito MONDEN |
4th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
5th Author's Name | Ken'ichi MATSUMOTO |
5th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
Date | 2004-10-18 |
Paper # | DE2004-111,DC2004-26 |
Volume (vol) | vol.104 |
Number (no) | 344 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |