{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T02:40:36Z","timestamp":1791772836936,"version":"4.3.4"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,8,28]],"date-time":"2019-08-28T00:00:00Z","timestamp":1566950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,8,28]],"date-time":"2019-08-28T00:00:00Z","timestamp":1566950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1007\/s10664-019-09758-x","type":"journal-article","created":{"date-parts":[[2019,8,28]],"date-time":"2019-08-28T07:02:58Z","timestamp":1566975778000},"page":"2258-2301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["What kind of questions do developers ask on Stack Overflow? A comparison of automated approaches to classify posts into question categories"],"prefix":"10.1007","volume":"25","author":[{"given":"Stefanie","family":"Beyer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Macho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Massimiliano","family":"Di Penta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Pinzger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,8,28]]},"reference":[{"key":"9758_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal R, Imieli\u0144ski T, Swami A (1993) Mining association rules between sets of items in large databases. In: International conference on management of data. ACM, pp 207\u2013216","DOI":"10.1145\/170035.170072"},{"key":"9758_CR2","unstructured":"Agrawal R, Srikant R, et al (1994) Fast algorithms for mining association rules. In: Proceedings of the International Conference of Very Large Data Bases, vol 1215, pp 487\u2013499"},{"key":"9758_CR3","doi-asserted-by":"crossref","unstructured":"Allamanis M, Sutton C (2013) Why, when, and what: Analyzing stack overflow questions by topic, type, and code. In: Proceedings of the Working Conference on Mining Software Repositories. IEEE, pp 53\u201356","DOI":"10.1109\/MSR.2013.6624004"},{"key":"9758_CR4","first-page":"1","volume":"19","author":"A Barua","year":"2012","unstructured":"Barua A, Thomas S, Hassan AE (2012) What are developers talking about? an analysis of topics and trends in Stack Overflow. Empir Softw Eng 19:1\u201336","journal-title":"Empir Softw Eng"},{"key":"9758_CR5","doi-asserted-by":"crossref","unstructured":"Beyer S, Pinzger M (2014) A manual categorization of android app development issues on Stack Overflow. In: Proceedings of the International Conference on Software Maintenance and Evolution. IEEE, pp 531\u2013535","DOI":"10.1109\/ICSME.2014.88"},{"key":"9758_CR6","doi-asserted-by":"crossref","unstructured":"Beyer S, Pinzger M (2016) Grouping android tag synonyms on Stack Overflow. In: Proceedings of the Working Conference on Mining Software Repositories. IEEE, pp 430\u2013440","DOI":"10.1145\/2901739.2901750"},{"key":"9758_CR7","unstructured":"Beyer S, Macho C, Di Penta M, Pinzger M (2017) Analyzing the relationships between android api classes and their references on stack overflow. Technical report, University of Klagenfurt University of Sannio"},{"key":"9758_CR8","doi-asserted-by":"crossref","unstructured":"Beyer S, Macho C, Pinzger M, Di Penta M (2018) Automatically classifying posts into question categories on stack overflow. In: Proceedings of the International Conference on Program Comprehension. ACM, pp 211\u2013221","DOI":"10.1145\/3196321.3196333"},{"key":"9758_CR9","doi-asserted-by":"publisher","unstructured":"Beyer S, Macho C, Di Penta M, Pinzger M (2019) qc_replication_package.zip. https:\/\/doi.org\/10.6084\/m9.figshare.8870123.v1","DOI":"10.6084\/m9.figshare.8870123.v1"},{"issue":"1","key":"9758_CR10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","journal-title":"Mach Learn"},{"key":"9758_CR11","doi-asserted-by":"crossref","unstructured":"Chaparro O, Lu J, Zampetti F, Moreno L, Di Penta M, Marcus A, Bavota G, Ng V (2017) Detecting missing information in bug descriptions. In: Proceedings of the Joint Meeting on Foundations of Software Engineering. ACM, pp 396\u2013407","DOI":"10.1145\/3106237.3106285"},{"key":"9758_CR12","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16:321\u2013357","journal-title":"J Artif Intell Res"},{"issue":"1","key":"9758_CR13","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/s13040-017-0155-3","volume":"10","author":"D Chicco","year":"2017","unstructured":"Chicco D (2017) Ten quick tips for machine learning in computational biology. BioData Min 10(1):35","journal-title":"BioData Min"},{"key":"9758_CR14","doi-asserted-by":"crossref","unstructured":"Coelho R, Almeida L, Gousios G, van Deursen A (2015) Unveiling exception handling bug hazards in android based on github and google code issues. In: Proceedings of the Working Conference of Mining Software Repositories. IEEE, pp 134\u2013145","DOI":"10.1109\/MSR.2015.20"},{"issue":"3","key":"9758_CR15","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273\u2013297","journal-title":"Mach Learn"},{"issue":"5","key":"9758_CR16","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","volume":"76","author":"JL Fleiss","year":"1971","unstructured":"Fleiss JL (1971) Measuring nominal scale agreement among many raters. Psychol Bullet 76(5):378","journal-title":"Psychol Bullet"},{"key":"9758_CR17","doi-asserted-by":"crossref","unstructured":"Fritz T, Murphy GC (2010) Using information fragments to answer the questions developers ask. In: Proceedings of the International Conference on Software Engineering. ACM, pp 175\u2013184","DOI":"10.1145\/1806799.1806828"},{"key":"9758_CR18","doi-asserted-by":"crossref","unstructured":"Fu W, Menzies T (2017) Easy over hard: a case study on deep learning. In: Proceedings of the Joint Meeting on Foundations of Software Engineering. ACM, pp 49\u201360","DOI":"10.1145\/3106237.3106256"},{"key":"9758_CR19","doi-asserted-by":"crossref","unstructured":"Hou D, Li L (2011) Obstacles in using frameworks and apis: an exploratory study of programmers\u2019 newsgroup discussions. In: Proceedings of the International Conference on Program Comprehension. IEEE, pp 91\u2013100","DOI":"10.1109\/ICPC.2011.21"},{"key":"9758_CR20","doi-asserted-by":"crossref","unstructured":"Joorabchi ME, Mesbah A, Kruchten P (2013) Real challenges in mobile app development. In: Proceedings of the International Symposium on Empirical Software Engineering and Measurement. ACM\/IEEE, pp 15\u201324","DOI":"10.1109\/ESEM.2013.9"},{"key":"9758_CR21","unstructured":"Kartik B, Karthik P, Ali M (2014) Mining questions asked by web developers. In: Proceedings of the Working Conference on Mining Software Repositories. ACM"},{"key":"9758_CR22","doi-asserted-by":"crossref","unstructured":"Kincaid JP, Fishburne Jr RP, Rogers RL, Chissom BS (1975) Derivation of new readability formulas (automated readability index fog count and flesch reading ease formula) for navy enlisted personnel","DOI":"10.21236\/ADA006655"},{"key":"9758_CR23","unstructured":"Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Ijcai, Montreal, vol 14, 1137\u20131145"},{"key":"9758_CR24","doi-asserted-by":"crossref","unstructured":"LaToza TD, Myers BA (2010) Hard-to-answer questions about code. In: Evaluation and usability of programming languages and tools. ACM, pp 8","DOI":"10.1145\/1937117.1937125"},{"key":"9758_CR25","unstructured":"Le TDB, Lo D (2015) Beyond support and confidence: Exploring interestingness measures for rule-based specification mining. In: Proceedings of the International Conference on Software Analysis, Evolution and Reengineering. IEEE, pp 331\u2013340"},{"key":"9758_CR26","doi-asserted-by":"crossref","unstructured":"Lee M, Jeon S, Song M (2018) Understanding user\u2019s interests in nosql databases in stack overflow. In: Proceedings of the International Conference on Emerging Databases. Springer, pp 128\u2013137","DOI":"10.1007\/978-981-10-6520-0_14"},{"issue":"4","key":"9758_CR27","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/0164-1212(87)90032-X","volume":"7","author":"S Letovsky","year":"1987","unstructured":"Letovsky S (1987) Cognitive processes in program comprehension. J Syst Softw 7(4):325\u2013339","journal-title":"J Syst Softw"},{"key":"9758_CR28","doi-asserted-by":"crossref","unstructured":"Li J, Xing Z, Kabir A (2018), Leveraging official content and social context to recommend software documentation. IEEE Transactions on Services Computing","DOI":"10.1109\/TSC.2018.2812729"},{"key":"9758_CR29","doi-asserted-by":"crossref","unstructured":"Linares-V\u00e1squez M, Dit B, Poshyvanyk D (2013) An exploratory analysis of mobile development issues using stack overflow. In: Proceedings of the Working Conference on Mining Software Repositories. IEEE Press, pp 93\u201396","DOI":"10.1109\/MSR.2013.6624014"},{"key":"9758_CR30","doi-asserted-by":"crossref","unstructured":"Loper E, Bird S (2002) Nltk: The natural language toolkit. In: Inproceedings of the ACL Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics. Philadelphia: Association for Computational Linguistics","DOI":"10.3115\/1118108.1118117"},{"key":"9758_CR31","unstructured":"Martinez M, Lecomte S (2017) Discovering discussion topics about development of cross-platform mobile applications using a cross-compiler development framework. arXiv: 1712.09569"},{"issue":"8","key":"9758_CR32","first-page":"639","volume":"12","author":"GH Mc Laughlin","year":"1969","unstructured":"Mc Laughlin GH (1969) Smog grading-a new readability formula. J Read 12 (8):639\u2013646","journal-title":"J Read"},{"key":"9758_CR33","doi-asserted-by":"crossref","unstructured":"Mehrab Z, Bin Yousuf R, Tahmid IA, Rifat S (2018) Mining developer questions about major web frameworks. In: Proceedings of the International Conference on Web Information Systems and Technologies. SciTePress, pp 191\u2013198","DOI":"10.5220\/0006929501910198"},{"key":"9758_CR34","unstructured":"Omran FNAA, Treude C (2017) Choosing an nlp library for analyzing software documentation: a systematic literature review and a series of experiments. In: Proceedings of the International Conference on Mining Software Repositories, pp 187\u2013197"},{"key":"9758_CR35","doi-asserted-by":"crossref","unstructured":"Ponzanelli L, Bacchelli A, Lanza M (2013) Seahawk: stack overflow in the ID. In: Proceedings of the 2013 International Conference on Software Engineering. IEEE Press, pp 1295\u20131298","DOI":"10.1109\/ICSE.2013.6606701"},{"key":"9758_CR36","doi-asserted-by":"crossref","unstructured":"Ponzanelli L, Bavota G, Di Penta M, Oliveto R, Lanza M (2014) Mining stackoverflow to turn the ide into a self-confident programming prompter. In: Proceedings of the Working Conference on Mining Software Repositories. ACM, pp 102\u2013111","DOI":"10.1145\/2597073.2597077"},{"key":"9758_CR37","unstructured":"Porter MF (1997) An algorithm for suffix stripping. In: Sparck Jones K, Willett P (eds) Readings in information retrieval. Morgan Kaufmann Publishers Inc, pp 313\u2013316"},{"key":"9758_CR38","unstructured":"Powers DM (2011) Evaluation: from precision, recall and f-measure to roc, informedness markedness and correlation"},{"issue":"3","key":"9758_CR39","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/s10994-011-5256-5","volume":"85","author":"J Read","year":"2011","unstructured":"Read J, Pfahringer B, Holmes F, Frank E (2011) Classifier chains for multi-label classification. Mach Learn 85(3):333","journal-title":"Mach Learn"},{"key":"9758_CR40","first-page":"1","volume":"21","author":"C Rosen","year":"2015","unstructured":"Rosen C, Shihab E (2015) What are mobile developers asking about? a large scale study using stack overflow. Empir Softw Eng 21:1\u201332","journal-title":"Empir Softw Eng"},{"key":"9758_CR41","unstructured":"Scalabrino S, Bavota G, Russo B, Oliveto R, Di Penta M (2017) Listening to the crowd for the release planning of mobile apps. IEEE Transactions on Software Engineering"},{"key":"9758_CR42","doi-asserted-by":"crossref","DOI":"10.1201\/9781315399102","volume-title":"Data mining with r: learning with case studies","author":"L Torgo","year":"2016","unstructured":"Torgo L (2016) Data mining with r: learning with case studies. CRC Press, Boca Raton"},{"key":"9758_CR43","doi-asserted-by":"crossref","unstructured":"Treude C, Barzilay O, Storey MA (2011) How do programmers ask and answer questions on the web? (NIER Track). In: Proceedings of the International Conference on Software Engineering. ACM, pp 804\u2013807","DOI":"10.1145\/1985793.1985907"},{"key":"9758_CR44","doi-asserted-by":"crossref","unstructured":"Villanes IK, Ascate SM, Gomes J, Dias-Neto AC (2017) What are software engineers asking about android testing on stack overflow?. In: Proceedings of the Brazilian Symposium on Software Engineering. ACM, pp 104\u2013113","DOI":"10.1145\/3131151.3131157"},{"key":"9758_CR45","doi-asserted-by":"crossref","unstructured":"Villarroel L, Bavota G, Russo B, Oliveto R, Di Penta M (2016) Release planning of mobile apps based on user reviews. In: Proceedings of the International Conference on Software Engineering. ACM, pp 14\u201324","DOI":"10.1145\/2884781.2884818"},{"key":"9758_CR46","doi-asserted-by":"crossref","unstructured":"Wen J, Sun G, Luo F (2016) Data driven development trend analysis of mainstream information technologies. In: Proceedings of the International Conference on Service Science. IEEE, pp 39\u201345","DOI":"10.1109\/ICSS.2016.13"},{"key":"9758_CR47","first-page":"1","volume":"24","author":"Y Wu","year":"2018","unstructured":"Wu Y, Wang S, Bezemer CP, Inoue K (2018) How do developers utilize source code from stack overflow?. Empir Softw Eng 24:1\u201337","journal-title":"Empir Softw Eng"},{"issue":"5","key":"9758_CR48","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1007\/s11390-016-1672-0","volume":"31","author":"X Yang","year":"2016","unstructured":"Yang X, Lo D, Xia X, Wan Z, Sun J (2016) What security questions do developers ask? a large-scale study of stack overflow posts. J Comput Sci Technol 31 (5):910\u2013924","journal-title":"J Comput Sci Technol"},{"key":"9758_CR49","doi-asserted-by":"crossref","unstructured":"Zhang Y, Hou D (2013) Extracting problematic api features from forum discussions. In: Proceedings of the International Conference on Program Comprehension. IEEE, pp 142\u2013151","DOI":"10.1109\/ICPC.2013.6613842"},{"issue":"4","key":"9758_CR50","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1145\/2652483","volume":"23","author":"P Zhang","year":"2014","unstructured":"Zhang P, Elbaum S (2014) Amplifying tests to validate exception handling code: an extended study in the mobile application domain. ACM Trans Softw Eng Methodol 23(4):32","journal-title":"ACM Trans Softw Eng Methodol"},{"key":"9758_CR51","doi-asserted-by":"crossref","unstructured":"Zou Y, Ye T, Lu Y, Mylopoulos J, Zhang L (2015) Learning to rank for question-oriented software text retrieval. In: Proceedings of the International Conference on Automated Software Engineering. IEEE, pp 1\u201311","DOI":"10.1109\/ASE.2015.24"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-019-09758-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10664-019-09758-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-019-09758-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,17]],"date-time":"2021-01-17T14:49:19Z","timestamp":1610894959000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10664-019-09758-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,28]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["9758"],"URL":"https:\/\/doi.org\/10.1007\/s10664-019-09758-x","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,28]]},"assertion":[{"value":"28 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}