@ARTICLE{Guerrouj13-EMSE-TIDIER,
   AUTHOR       = {Latifa Guerrouj and Di Penta, Massimiliano and 
      Yann-Ga�l Gu�h�neuc and Giuliano Antoniol},
   JOURNAL      = {Empirical Software Engineering (EMSE)},
   TITLE        = {An Experimental Investigation on the Effects of Context 
      on Source Code Identifiers Splitting and Expansion},
   YEAR         = {2013},
   MONTH        = {July},
   NOTE         = {45 pages.},
   NUMBER       = {6},
   PAGES        = {1--48},
   VOLUME       = {19},
   EDITOR       = {Victor R. Basili and Lionel C. Briand},
   KEYWORDS     = {Topic: <b>Identifier analysis</b>, Venue: <b>EMSE</b>},
   PUBLISHER    = {Springer},
   URL          = {http://www.ptidej.net/publications/documents/EMSE13.doc.pdf},
   ABSTRACT     = {Recent and past studies indicate that source code 
      lexicon plays an important role in program comprehension. Developers 
      often compose source code identifiers with abbreviated words and 
      acronyms, and do not always use consistent mechanisms and explicit 
      separators when creating identifiers. Such choices and 
      inconsistencies impede the work of developers that must understand 
      identifiers by decomposing them into their component terms, and 
      mapping them onto dictionary, application or domain words. When 
      software documentation is scarce, outdated or simply not available, 
      developers must therefore use the available contextual information to 
      understand the source code. This paper aims at investigating how 
      developers split and expand source code identifiers, and, 
      specifically, the extent to which different kinds of contextual 
      information could support such a task. In particular, we consider (i) 
      an internal context consisting of the content of functions and source 
      code files in which the identifiers are located, and (ii) an external 
      context involving external documentation. We conducted a family of 
      two experiments with 63 participants, including bachelor, master, 
      Ph.D. students, and post-docs. We randomly sampled a set of 50 
      identifiers from a corpus of open source C programs and we asked 
      participants to split and expand them with the availability (or not) 
      of internal and external contexts. We report evidence on the 
      usefulness of contextual information for identifier splitting and 
      acronym/abbreviation expansion. We observe that the source code files 
      are more helpful than just looking at function source code, and that 
      the application-level contextual information does not help any 
      further. The availability of external sources of information only 
      helps in some circumstances. Also, in some cases, we observe that 
      participants better expanded acronyms than abbreviations, although in 
      most cases both exhibit the same level of accuracy. Finally, results 
      indicated that the knowledge of English plays a significant effect in 
      identifier splitting/expansion. The obtained results confirm the 
      conjecture that contextual information is useful in program 
      comprehension, including when developers split and expand identifiers 
      to understand them. We hypothesize that the integration of identifier 
      splitting and expansion tools with IDE could help to improve 
      developers' productivity.}
}

{"_id":"dquRXJqQcvJSnmimT","bibbaseid":"guerrouj-dipenta-guhneuc-antoniol-anexperimentalinvestigationontheeffectsofcontextonsourcecodeidentifierssplittingandexpansion-2013","downloads":0,"creationDate":"2018-01-17T20:29:42.299Z","title":"An Experimental Investigation on the Effects of Context on Source Code Identifiers Splitting and Expansion","author_short":["Guerrouj, L.","Di Penta, M.","Gu�h�neuc, Y.","Antoniol, G."],"year":2013,"bibtype":"article","biburl":"http://www.yann-gael.gueheneuc.net/Work/Publications/Biblio/complete-bibliography.bib","bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Latifa"],"propositions":[],"lastnames":["Guerrouj"],"suffixes":[]},{"propositions":[],"lastnames":["Di","Penta"],"firstnames":["Massimiliano"],"suffixes":[]},{"firstnames":["Yann-Ga�l"],"propositions":[],"lastnames":["Gu�h�neuc"],"suffixes":[]},{"firstnames":["Giuliano"],"propositions":[],"lastnames":["Antoniol"],"suffixes":[]}],"journal":"Empirical Software Engineering (EMSE)","title":"An Experimental Investigation on the Effects of Context on Source Code Identifiers Splitting and Expansion","year":"2013","month":"July","note":"45 pages.","number":"6","pages":"1–48","volume":"19","editor":[{"firstnames":["Victor","R."],"propositions":[],"lastnames":["Basili"],"suffixes":[]},{"firstnames":["Lionel","C."],"propositions":[],"lastnames":["Briand"],"suffixes":[]}],"keywords":"Topic: <b>Identifier analysis</b>, Venue: <b>EMSE</b>","publisher":"Springer","url":"http://www.ptidej.net/publications/documents/EMSE13.doc.pdf","abstract":"Recent and past studies indicate that source code lexicon plays an important role in program comprehension. Developers often compose source code identifiers with abbreviated words and acronyms, and do not always use consistent mechanisms and explicit separators when creating identifiers. Such choices and inconsistencies impede the work of developers that must understand identifiers by decomposing them into their component terms, and mapping them onto dictionary, application or domain words. When software documentation is scarce, outdated or simply not available, developers must therefore use the available contextual information to understand the source code. This paper aims at investigating how developers split and expand source code identifiers, and, specifically, the extent to which different kinds of contextual information could support such a task. In particular, we consider (i) an internal context consisting of the content of functions and source code files in which the identifiers are located, and (ii) an external context involving external documentation. We conducted a family of two experiments with 63 participants, including bachelor, master, Ph.D. students, and post-docs. We randomly sampled a set of 50 identifiers from a corpus of open source C programs and we asked participants to split and expand them with the availability (or not) of internal and external contexts. We report evidence on the usefulness of contextual information for identifier splitting and acronym/abbreviation expansion. We observe that the source code files are more helpful than just looking at function source code, and that the application-level contextual information does not help any further. The availability of external sources of information only helps in some circumstances. Also, in some cases, we observe that participants better expanded acronyms than abbreviations, although in most cases both exhibit the same level of accuracy. Finally, results indicated that the knowledge of English plays a significant effect in identifier splitting/expansion. The obtained results confirm the conjecture that contextual information is useful in program comprehension, including when developers split and expand identifiers to understand them. We hypothesize that the integration of identifier splitting and expansion tools with IDE could help to improve developers' productivity.","bibtex":"@ARTICLE{Guerrouj13-EMSE-TIDIER,\r\n AUTHOR = {Latifa Guerrouj and Di Penta, Massimiliano and \r\n Yann-Ga�l Gu�h�neuc and Giuliano Antoniol},\r\n JOURNAL = {Empirical Software Engineering (EMSE)},\r\n TITLE = {An Experimental Investigation on the Effects of Context \r\n on Source Code Identifiers Splitting and Expansion},\r\n YEAR = {2013},\r\n MONTH = {July},\r\n NOTE = {45 pages.},\r\n NUMBER = {6},\r\n PAGES = {1--48},\r\n VOLUME = {19},\r\n EDITOR = {Victor R. Basili and Lionel C. Briand},\r\n KEYWORDS = {Topic: <b>Identifier analysis</b>, Venue: <b>EMSE</b>},\r\n PUBLISHER = {Springer},\r\n URL = {http://www.ptidej.net/publications/documents/EMSE13.doc.pdf},\r\n ABSTRACT = {Recent and past studies indicate that source code \r\n lexicon plays an important role in program comprehension. Developers \r\n often compose source code identifiers with abbreviated words and \r\n acronyms, and do not always use consistent mechanisms and explicit \r\n separators when creating identifiers. Such choices and \r\n inconsistencies impede the work of developers that must understand \r\n identifiers by decomposing them into their component terms, and \r\n mapping them onto dictionary, application or domain words. When \r\n software documentation is scarce, outdated or simply not available, \r\n developers must therefore use the available contextual information to \r\n understand the source code. This paper aims at investigating how \r\n developers split and expand source code identifiers, and, \r\n specifically, the extent to which different kinds of contextual \r\n information could support such a task. In particular, we consider (i) \r\n an internal context consisting of the content of functions and source \r\n code files in which the identifiers are located, and (ii) an external \r\n context involving external documentation. We conducted a family of \r\n two experiments with 63 participants, including bachelor, master, \r\n Ph.D. students, and post-docs. We randomly sampled a set of 50 \r\n identifiers from a corpus of open source C programs and we asked \r\n participants to split and expand them with the availability (or not) \r\n of internal and external contexts. We report evidence on the \r\n usefulness of contextual information for identifier splitting and \r\n acronym/abbreviation expansion. We observe that the source code files \r\n are more helpful than just looking at function source code, and that \r\n the application-level contextual information does not help any \r\n further. The availability of external sources of information only \r\n helps in some circumstances. Also, in some cases, we observe that \r\n participants better expanded acronyms than abbreviations, although in \r\n most cases both exhibit the same level of accuracy. Finally, results \r\n indicated that the knowledge of English plays a significant effect in \r\n identifier splitting/expansion. The obtained results confirm the \r\n conjecture that contextual information is useful in program \r\n comprehension, including when developers split and expand identifiers \r\n to understand them. We hypothesize that the integration of identifier \r\n splitting and expansion tools with IDE could help to improve \r\n developers' productivity.}\r\n}\r\n\r\n","author_short":["Guerrouj, L.","Di Penta, M.","Gu�h�neuc, Y.","Antoniol, G."],"editor_short":["Basili, V. R.","Briand, L. C."],"key":"Guerrouj13-EMSE-TIDIER","id":"Guerrouj13-EMSE-TIDIER","bibbaseid":"guerrouj-dipenta-guhneuc-antoniol-anexperimentalinvestigationontheeffectsofcontextonsourcecodeidentifierssplittingandexpansion-2013","role":"author","urls":{"Paper":"http://www.ptidej.net/publications/documents/EMSE13.doc.pdf"},"keyword":["Topic: <b>Identifier analysis</b>","Venue: <b>EMSE</b>"],"metadata":{"authorlinks":{"gu�h�neuc, y":"https://bibbase.org/show?bib=http%3A%2F%2Fwww.yann-gael.gueheneuc.net%2FWork%2FPublications%2FBiblio%2Fcomplete-bibliography.bib&msg=embed","guéhéneuc, y":"https://bibbase.org/show?bib=http://www.yann-gael.gueheneuc.net/Work/BibBase/guehene%20(automatically%20cleaned).bib"}},"downloads":0},"search_terms":["experimental","investigation","effects","context","source","code","identifiers","splitting","expansion","guerrouj","di penta","gu�h�neuc","antoniol"],"keywords":["topic: <b>identifier analysis</b>","venue: <b>emse</b>"],"authorIDs":["2tFXMaTSHJKEB5ebi","2wY5eBcsYmbPNfmMS","36dm7jaw5EK5Wrr4D","3NxaNKic3nkXi568L","3S5Dkpx7DNefzJrnf","3afmfmoPr4SHa8B5F","3wmHB7JoQbQz2ujun","4YBWWbao6RKgiyGJE","4jZj9tB4SJ8zEEgHk","5CvA2hsaib2bPMaef","5TFJbxqRDGFj2P8Rg","5a5fb236a39f2c3645000032","5a8f17e006df23bc34000020","5cx79LBmaWcihgM4J","5de9a6425b51bcde01000042","5dee1197584fb4df010000fc","5df228a41e4fe9df0100012c","5df617f72b34d0de0100008b","5dfa14782e791dde010000ea","5dfe3d5e68d95dde01000080","5e02525b6ffa15df0100009f","5e0662c07da1d1de0100021a","5e093e8b934cacdf0100008b","5e0a61673eccf6e001000016","5e0b75b7e73cd6de010000f9","5e0d4ca6ae5827df0100007f","5e0ddf08552b25df01000137","5e0e5c41ac7d11df010000a3","5e1268e7a4cabfdf0100002c","5e12c45a70e2c4f201000043","5e157809f1f31adf01000006","5e162ca1df1bb4de01000123","5e185cff809b84f201000091","5e1a6c39b16ec5df0100000f","5e21b27e96aea7de01000084","5e22c57e49e2b4df0100000f","5e23c2aeb93b51de01000030","5e245835079bb2df0100007d","5e24fa3e2e79a1f201000027","5e26252f408641df01000161","5e26bfbd8535cedf0100005c","5e280fd1f860fcde0100006a","5e2a827f881468de01000080","5e2eb321b84405df01000128","5e2ef635e374eede0100001a","5e2fd6a74e91a9df01000010","5e3266bb5633c9de01000068","5e32ab0ee17accde0100012a","5e32bdec466076df010000d9","5e32d603150c84df01000068","5e34fb145978bef2010000a6","5e36bc8e7b975dde0100009a","5e389940030bcadf010001b4","5e39dd9a3687dddf010000a4","5e3ad173f2a00cdf01000206","5e3dcd50d51253de0100003d","5e3e8713666d79df010000a6","5e3ed80986a596de010000b9","5e3fefe1add5fbde01000087","5e409c79d668c6de010000c7","5e41795ed9f47bee01000194","5e41cd5be7c67ade010000eb","5e42ef1ca6f4a6f2010001eb","5e46dcb342fb31df01000113","5e46f12c461d04f201000078","5e478c9e27a0c8de010000ef","5e47fb06385298df010000b2","5e4add1941072bdf01000011","5e4c1c792dc400de0100011a","5e4c6262271596df010001b9","5e4f0360338acfde01000156","5e4f11b0e5389bde0100007e","5e530b976d68b8df010000a5","5e54ad6d929495df0100007c","5e57161b429006de0100005a","5e57839fcef9b7de0100003c","5e580f5a6a456fde0100004f","5e5afa78038583de010000f7","5e5b477174a3e7df010000b7","5e5d370173eb2edf01000038","5e5fca336b32b0f20100011b","5e60e7f0839e59df010000e8","5e6377cfae1c4dde0100011e","5e657007de41b9df0100017a","5e676f0910be53de0100001a","5gPbX6aQJFjpv2Na9","6eE2yRdMDQr2WGXuA","6iHE5tuM7yTfLd2pA","7BPWyvMr5e6bzbk7T","7RFwhpGkpZRsLwnmB","7amRA4ALcR2mksheF","7mkQL8eiftj5bGMzB","8jPjKehCMsj7ncvxN","8peLXfWtCSic5n7oz","95eRgTcabnJwF46f3","9Ba9JxkjQBCeGBZKg","9DjgvzQrx27uxbyJj","9HD56d3k5yrB9H9oq","9RtPuXNyeS3k8LM9J","9diLYpd8cMmjBh54T","9nx6Yv3XREwJDyRms","AfJhKcg96muyPdu7S","BGvchZsjW7Wejj9Cz","BYwdHpGr6xT5vmE5C","Bah6LM7GXdXTy8GGA","BmH2ytt7sXwPHcrse","CqJYxtqe6qBbtd5yz","D4kEZ2JcWCoMvRPy7","DFWW7D6Y7X57n4cbM","DSorPqHDfrFiNM5Ew","DWXisKXaQArvre3QL","DwBm6isMpKSHHkhAd","E88raoktD8ANF92Yu","EAjLox7ycbofcCXce","F8rzFhY9yWA7pBX4j","G3iynDKjz9BHJbrdg","GJw6mQETXADSCZuuk","GWK5669HLqPyYMQ5J","GibAXjj4xXdFT8qWh","HzFZpgGcfabjAp9x6","KJ4eYziy6hanF9kr9","Kcyu7uncEFiYzYP2D","N4zzhqcywSzDDYsdh","NCDg3xE2mPcNAu7LX","NvgbTAz3hZ9SevZvd","QbcDS3wK43sRASvgu","S3b7Bb9wwfpByQgbo","SXJaeFCgBDJ5HAHtj","T5nL8TGrggoLAF8Dj","W9vT8YcCNFEcp9mWQ","WZ5CpBEFNsb2ivfah","XxviSwRxhwgNwsraH","Z2Zs662GpXqKBEAMc","ZKYFgjHGm7PE4Y2kv","a5qpGirN3B5BLKdMh","ahGA65oGDChNYp7Mb","bA7pGCMS9AB2RBo2p","bTQb3TcrbBShtqFPS","cYnqisf4wzBsM7MF5","cjHpaYiWD5eX7btH4","ckrbesqi3pWqfF2nP","dH8EsWHZtCFuQk5bq","dS5kvBMnk3LMQe56w","eXsFRMzE7WfbHbBL4","fmmsBu4m6ayKtuopf","hdXr3PD8cHNWyAdCe","hgZxckC87u2A57teF","juvCjffHJaPQf44im","keQBT2Apb9yaev8AH","myHdF8zARwW5uGmFs","nJLfaznnYgFqWQQrv","onghitNWSvN2FpCaN","osgPwDW2y5KDXRa2i","pAWFMDHu5dNixqPAq","pLvmgrCjMeDYJiJxB","q4azvWakEjp2TQM7S","qBee6Md9YwRKwkeW3","qQky2Csek4mroLn2P","tJz4YBCqAzZAzek5d","tLtjttw8dEqF6YQ4s","uQ6jCrPijzAmZyfXz","vGEaFNt7mm92Z7GXc","vRkMmE65HSFpCk6FW","vsEsf8FR3Fxb6z7fJ","x5ejzvDeXCc89Dukv","xEQyC5shxpYySSJJm","xhwDdvQ7MYxa6keXm","xkviMnkrGBneANvMr","y64rFMcyp7tDsBrJQ","yBYJWSShoKkMG8aPE","yQPghCwQv22kf6dFq","yd5sCxaEiu5vWizTq"],"dataSources":["Sed98LbBeGaXxenrM","8vn5MSGYWB4fAx9Z4"]}