@conference{28f171f75218419eb759b590aac0123c,
  title    = "Automatic library categorization",
  abstract = "Software ecosystems contain several types of artefacts such as libraries, documentation and source code files. Recent studies show that the Maven software ecosystem alone already contains over 2.8 million artefacts and over 70, 000 libraries. Given the size of the ecosystem, selecting a library represents a challenge to its users.The MVNRepository website offers a category-based search func- tionality as a solution. However, not all of the libraries have been categorised, which leads to incomplete search results. This work proposes an approach to the automatic categorisation of libraries through machine learning classifiers trained on class and method names. Our preliminary results show that the approach is accurate, suggesting that large-scale applications may be feasible.",
  keywords = "Software Ecosystems, API Category, Text Classification",
  author   = "{Velazquez Rodriguez}, {Camilo Ernesto} and {De Roover}, Coen",
  year     = "2020",
  doi      = "10.1145/3387940.3392186",
  language = "English",
  pages    = "733--734",
  note     = "3rd International Workshop on Software Health ; Conference date: 05-10-2020 Through 11-10-2020",
}

{"_id":"Mhhb7fpwopGZ6ABSC","bibbaseid":"velazquezrodriguez-deroover-automaticlibrarycategorization-2020","author_short":["Velazquez Rodriguez, C.","De Roover, C."],"bibdata":{"bibtype":"conference","type":"conference","title":"Automatic library categorization","abstract":"Software ecosystems contain several types of artefacts such as libraries, documentation and source code files. Recent studies show that the Maven software ecosystem alone already contains over 2.8 million artefacts and over 70, 000 libraries. Given the size of the ecosystem, selecting a library represents a challenge to its users.The MVNRepository website offers a category-based search func- tionality as a solution. However, not all of the libraries have been categorised, which leads to incomplete search results. This work proposes an approach to the automatic categorisation of libraries through machine learning classifiers trained on class and method names. Our preliminary results show that the approach is accurate, suggesting that large-scale applications may be feasible.","keywords":"Software Ecosystems, API Category, Text Classification","author":[{"propositions":[],"lastnames":["Velazquez Rodriguez"],"firstnames":["Camilo Ernesto"],"suffixes":[]},{"propositions":[],"lastnames":["De Roover"],"firstnames":["Coen"],"suffixes":[]}],"year":"2020","doi":"10.1145/3387940.3392186","language":"English","pages":"733–734","note":"3rd International Workshop on Software Health ; Conference date: 05-10-2020 Through 11-10-2020","bibtex":"@conference{28f171f75218419eb759b590aac0123c,\n title = \"Automatic library categorization\",\n abstract = \"Software ecosystems contain several types of artefacts such as libraries, documentation and source code files. Recent studies show that the Maven software ecosystem alone already contains over 2.8 million artefacts and over 70, 000 libraries. Given the size of the ecosystem, selecting a library represents a challenge to its users.The MVNRepository website offers a category-based search func- tionality as a solution. However, not all of the libraries have been categorised, which leads to incomplete search results. This work proposes an approach to the automatic categorisation of libraries through machine learning classifiers trained on class and method names. Our preliminary results show that the approach is accurate, suggesting that large-scale applications may be feasible.\",\n keywords = \"Software Ecosystems, API Category, Text Classification\",\n author = \"{Velazquez Rodriguez}, {Camilo Ernesto} and {De Roover}, Coen\",\n year = \"2020\",\n doi = \"10.1145/3387940.3392186\",\n language = \"English\",\n pages = \"733--734\",\n note = \"3rd International Workshop on Software Health ; Conference date: 05-10-2020 Through 11-10-2020\",\n}","author_short":["Velazquez Rodriguez, C.","De Roover, C."],"key":"28f171f75218419eb759b590aac0123c","id":"28f171f75218419eb759b590aac0123c","bibbaseid":"velazquezrodriguez-deroover-automaticlibrarycategorization-2020","role":"author","urls":{},"keyword":["Software Ecosystems","API Category","Text Classification"],"metadata":{"authorlinks":{}}},"bibtype":"conference","biburl":"http://soft.vub.ac.be/~cderoove/works.bib","dataSources":["abyQtmN3vDJoFXPPD"],"keywords":["software ecosystems","api category","text classification"],"search_terms":["automatic","library","categorization","velazquez rodriguez","de roover"],"title":"Automatic library categorization","year":2020}