MUDABlue: An automatic categorization system for Open Source repositories Export

@article{citeulike:671458, abstract = {Open Source communities typically use a software repository to archive various software projects with their source code, mailing list discussions, documentation, bug reports, and so forth. For example, SourceForge currently hosts over seventy thousand Open Source software systems. Because of the size of the rich information content, such repositories offer numerous opportunities for sharing information among projects. For example, one would like to know a set of projects that are related or similar to each other, so that the project groups can collaborate and share their work. With thousands of projects in typical repositories, however, manually locating related projects can be difficult. Hence, we propose MUDABlue, a tool that automatically categorizes software systems. MUDABlue has three major aspects: (1) it relies on no other information than the source code, (2) it determines category sets automatically, and (3) it allows a software system to be a member of multiple categories. MUDABlue has a Web interface to visualize determined categories, which eases browsing a software repository. We show the effectiveness of MUDABlue's categorization capability by comparing its generated categories with that of some other existing research tools.}, author = {Kawaguchi, Shinji and Garg, Pankaj K. and Matsushita, Makoto and Inoue, Katsuro}, booktitle = {Selected papers from the 11th Asia Pacific Software Engineering Conference (APSEC2004)}, citeulike-article-id = {671458}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.jss.2005.06.044}, citeulike-linkout-1 = {http://www.sciencedirect.com/science/article/B6V0N-4J8D8V2-1/2/35ee6dc76ad4cfacb28b315d92388e82}, doi = {10.1016/j.jss.2005.06.044}, journal = {Journal of Systems and Software}, keywords = {mda4fop, splc2}, month = {July}, number = {7}, pages = {939--953}, posted-at = {2006-05-26 15:31:17}, priority = {2}, title = {MUDABlue: An automatic categorization system for Open Source repositories}, url = {http://dx.doi.org/10.1016/j.jss.2005.06.044}, volume = {79}, year = {2006} }

TY - JOUR ID - citeulike:671458 L3 - citeulike-article-id:671458 N2 - Open Source communities typically use a software repository to archive various software projects with their source code, mailing list discussions, documentation, bug reports, and so forth. For example, SourceForge currently hosts over seventy thousand Open Source software systems. Because of the size of the rich information content, such repositories offer numerous opportunities for sharing information among projects. For example, one would like to know a set of projects that are related or similar to each other, so that the project groups can collaborate and share their work. With thousands of projects in typical repositories, however, manually locating related projects can be difficult. Hence, we propose MUDABlue, a tool that automatically categorizes software systems. MUDABlue has three major aspects: (1) it relies on no other information than the source code, (2) it determines category sets automatically, and (3) it allows a software system to be a member of multiple categories. MUDABlue has a Web interface to visualize determined categories, which eases browsing a software repository. We show the effectiveness of MUDABlue's categorization capability by comparing its generated categories with that of some other existing research tools. IS - 7 JF - Journal of Systems and Software EP - 953 TI - MUDABlue: An automatic categorization system for Open Source repositories VL - 79 T2 - Selected papers from the 11th Asia Pacific Software Engineering Conference (APSEC2004) SP - 939 KW - mda4fop KW - splc2 AU - Kawaguchi, Shinji AU - Garg, Pankaj AU - Matsushita, Makoto AU - Inoue, Katsuro PY - 2006/07// UR - http://dx.doi.org/10.1016/j.jss.2005.06.044 ER -