@ARTICLE{Barbez19-JSS-AntiPatternsEsembleMethod,
   AUTHOR       = {Antoine Barbez and Foutse Khomh and Yann-Ga�l Gu�h�neuc},
   JOURNAL      = {Journal of Systems and Software (JSS)},
   TITLE        = {A Machine-learning based Ensemble Method for 
      Anti-patterns Detection},
   YEAR         = {2020},
   MONTH        = {March},
   NOTE         = {15 pages.},
   OPTNUMBER    = {},
   PAGES        = {110486},
   VOLUME       = {161},
   EDITOR       = {Paris Avgeriou and David Shepherd},
   KEYWORDS     = {Topic: <b>Code and design smells</b>, Venue: <b>JSS</b>},
   PUBLISHER    = {Elsevier},
   URL          = {http://www.ptidej.net/publications/documents/JSS20a.doc.pdf},
   ABSTRACT     = {Anti-patterns are poor solutions to recurring design 
      problems. Several empirical studies have highlighted their negative 
      impact on program comprehension, maintainability, as well as 
      fault-proneness. A variety of detection approaches have been proposed 
      to identify their occurrences in source code. However, these 
      approaches can identify only a subset of the occurrences and report 
      large numbers of false positives and misses. Furthermore, a low 
      agreement is generally observed among different approaches. Recent 
      studies have shown the potential of machine-learning models to 
      improve this situation. However, such algorithms require large sets 
      of manually-produced training-data, which often limits their 
      application in practice. In this paper, we present SMAD (SMart 
      Aggregation of Anti-patterns Detectors), a machine-learning based 
      ensemble method to aggregate various anti-patterns detection 
      approaches on the basis of their internal detection rules. Thus, our 
      method uses several detection tools to produce an improved prediction 
      from a reasonable number of training examples. We implemented SMAD 
      for the detection of two well known anti-patterns: God Class and 
      Feature Envy. With the results of our experiments conducted on eight 
      java projects, we show that: (1) Our method clearly improves the so 
      aggregated tools; (2) SMAD significantly outperforms other ensemble 
      methods.}
}

{"_id":"55Rtcwo2WecmYvb8J","bibbaseid":"barbez-khomh-guhneuc-amachinelearningbasedensemblemethodforantipatternsdetection-2020","author_short":["Barbez, A.","Khomh, F.","Gu�h�neuc, Y."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Antoine"],"propositions":[],"lastnames":["Barbez"],"suffixes":[]},{"firstnames":["Foutse"],"propositions":[],"lastnames":["Khomh"],"suffixes":[]},{"firstnames":["Yann-Ga�l"],"propositions":[],"lastnames":["Gu�h�neuc"],"suffixes":[]}],"journal":"Journal of Systems and Software (JSS)","title":"A Machine-learning based Ensemble Method for Anti-patterns Detection","year":"2020","month":"March","note":"15 pages.","optnumber":"","pages":"110486","volume":"161","editor":[{"firstnames":["Paris"],"propositions":[],"lastnames":["Avgeriou"],"suffixes":[]},{"firstnames":["David"],"propositions":[],"lastnames":["Shepherd"],"suffixes":[]}],"keywords":"Topic: <b>Code and design smells</b>, Venue: <b>JSS</b>","publisher":"Elsevier","url":"http://www.ptidej.net/publications/documents/JSS20a.doc.pdf","abstract":"Anti-patterns are poor solutions to recurring design problems. Several empirical studies have highlighted their negative impact on program comprehension, maintainability, as well as fault-proneness. A variety of detection approaches have been proposed to identify their occurrences in source code. However, these approaches can identify only a subset of the occurrences and report large numbers of false positives and misses. Furthermore, a low agreement is generally observed among different approaches. Recent studies have shown the potential of machine-learning models to improve this situation. However, such algorithms require large sets of manually-produced training-data, which often limits their application in practice. In this paper, we present SMAD (SMart Aggregation of Anti-patterns Detectors), a machine-learning based ensemble method to aggregate various anti-patterns detection approaches on the basis of their internal detection rules. Thus, our method uses several detection tools to produce an improved prediction from a reasonable number of training examples. We implemented SMAD for the detection of two well known anti-patterns: God Class and Feature Envy. With the results of our experiments conducted on eight java projects, we show that: (1) Our method clearly improves the so aggregated tools; (2) SMAD significantly outperforms other ensemble methods.","bibtex":"@ARTICLE{Barbez19-JSS-AntiPatternsEsembleMethod,\r\n AUTHOR = {Antoine Barbez and Foutse Khomh and Yann-Ga�l Gu�h�neuc},\r\n JOURNAL = {Journal of Systems and Software (JSS)},\r\n TITLE = {A Machine-learning based Ensemble Method for \r\n Anti-patterns Detection},\r\n YEAR = {2020},\r\n MONTH = {March},\r\n NOTE = {15 pages.},\r\n OPTNUMBER = {},\r\n PAGES = {110486},\r\n VOLUME = {161},\r\n EDITOR = {Paris Avgeriou and David Shepherd},\r\n KEYWORDS = {Topic: <b>Code and design smells</b>, Venue: <b>JSS</b>},\r\n PUBLISHER = {Elsevier},\r\n URL = {http://www.ptidej.net/publications/documents/JSS20a.doc.pdf},\r\n ABSTRACT = {Anti-patterns are poor solutions to recurring design \r\n problems. Several empirical studies have highlighted their negative \r\n impact on program comprehension, maintainability, as well as \r\n fault-proneness. A variety of detection approaches have been proposed \r\n to identify their occurrences in source code. However, these \r\n approaches can identify only a subset of the occurrences and report \r\n large numbers of false positives and misses. Furthermore, a low \r\n agreement is generally observed among different approaches. Recent \r\n studies have shown the potential of machine-learning models to \r\n improve this situation. However, such algorithms require large sets \r\n of manually-produced training-data, which often limits their \r\n application in practice. In this paper, we present SMAD (SMart \r\n Aggregation of Anti-patterns Detectors), a machine-learning based \r\n ensemble method to aggregate various anti-patterns detection \r\n approaches on the basis of their internal detection rules. Thus, our \r\n method uses several detection tools to produce an improved prediction \r\n from a reasonable number of training examples. We implemented SMAD \r\n for the detection of two well known anti-patterns: God Class and \r\n Feature Envy. With the results of our experiments conducted on eight \r\n java projects, we show that: (1) Our method clearly improves the so \r\n aggregated tools; (2) SMAD significantly outperforms other ensemble \r\n methods.}\r\n}\r\n\r\n","author_short":["Barbez, A.","Khomh, F.","Gu�h�neuc, Y."],"editor_short":["Avgeriou, P.","Shepherd, D."],"key":"Barbez19-JSS-AntiPatternsEsembleMethod","id":"Barbez19-JSS-AntiPatternsEsembleMethod","bibbaseid":"barbez-khomh-guhneuc-amachinelearningbasedensemblemethodforantipatternsdetection-2020","role":"author","urls":{"Paper":"http://www.ptidej.net/publications/documents/JSS20a.doc.pdf"},"keyword":["Topic: <b>Code and design smells</b>","Venue: <b>JSS</b>"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"http://www.yann-gael.gueheneuc.net/Work/Publications/Biblio/complete-bibliography.bib","dataSources":["8vn5MSGYWB4fAx9Z4"],"keywords":["topic: <b>code and design smells</b>","venue: <b>jss</b>"],"search_terms":["machine","learning","based","ensemble","method","anti","patterns","detection","barbez","khomh","gu�h�neuc"],"title":"A Machine-learning based Ensemble Method for Anti-patterns Detection","year":2020}