references.bib

@article{Robillard:2009,
  title={What makes APIs hard to learn? Answers from developers},
  author={Robillard, Martin P.},
  journal={Software, IEEE},
  volume={26},
  number={6},
  pages={27--34},
  year={2009},
  publisher={IEEE}
}

@article{Uddin:2015,
  title={How API Documentation Fails},
  author={Uddin, Gias and Robillard, Martin P.},
  journal={Software, IEEE},
  volume={32},
  number={4},
  pages={68--75},
  year={2015},
  publisher={IEEE}
}

@book{Spinellis:2006,
  title={Code quality: the open source perspective},
  author={Spinellis, Diomidis},
  year={2006},
  publisher={Adobe Press}
}

@inproceedings{Hoffmann:2007,
  title={Assieme: finding and leveraging implicit references in a web search interface for programmers},
  author={Hoffmann, Raphael and Fogarty, James and Weld, Daniel S},
  booktitle={Proceedings of the 20th annual ACM symposium on User interface software and technology},
  pages={13--22},
  year={2007},
  organization={ACM}
}

@inproceedings{Khatoon:2011,
  title={An evaluation of source code mining techniques},
  author={Khatoon, Shahida and Mahmood, Arif and Li, Guohui},
  booktitle={Fuzzy Systems and Knowledge Discovery (FSKD), 2011 Eighth International Conference on},
  volume={3},
  pages={1929--1933},
  year={2011},
  organization={IEEE}
}

@article{Ishag:2016,
  title={Highlighting Current Issues in API Usage Mining to Enhance Software Reusability},
  author={ISHAG, MUSA IBRAHIM M and PARK, HYUN WOO and LI, DINGKUN and RYU, KEUN HO},
  year={2016}
}

@inproceedings{Agrawal:1994,
  title={Fast algorithms for mining association rules},
  author={Agrawal, Rakesh and Srikant, Ramakrishnan and others},
  booktitle={Proc. 20th int. conf. very large data bases, VLDB},
  volume={1215},
  pages={487--499},
  year={1994}
}

@article{Zaki:2001,
  title={SPADE: An efficient algorithm for mining frequent sequences},
  author={Zaki, Mohammed J},
  journal={Machine learning},
  volume={42},
  number={1-2},
  pages={31--60},
  year={2001},
  publisher={Springer}
}

@inproceedings{Wang:2004,
  title={BIDE: Efficient mining of frequent closed sequences},
  author={Wang, Jianyong and Han, Jiawei},
  booktitle={Data Engineering, 2004. Proceedings. 20th International Conference on},
  pages={79--90},
  year={2004},
  organization={IEEE}
}

@article{Fowkes:2016,
  title={A Subsequence Interleaving Model for Sequential Pattern Mining},
  author={Fowkes, Jaroslav and Sutton, Charles},
  journal={arXiv preprint arXiv:1602.05012},
  year={2016}
}

@inproceedings{Han:2000,
  title={Mining frequent patterns without candidate generation},
  author={Han, Jiawei and Pei, Jian and Yin, Yiwen},
  booktitle={ACM Sigmod Record},
  volume={29},
  number={2},
  pages={1--12},
  year={2000},
  organization={ACM}
}

@book{Rajaraman:2012,
  title={Mining of massive datasets},
  author={Rajaraman, Anand and Ullman, Jeffrey D and Ullman, Jeffrey David and Ullman, Jeffrey David},
  volume={1},
  year={2012},
  publisher={Cambridge University Press Cambridge}
}

@inproceedings{Li:2005,
  title={PR-Miner: automatically extracting implicit programming rules and detecting violations in large software code},
  author={Li, Zhenmin and Zhou, Yuanyuan},
  booktitle={ACM SIGSOFT Software Engineering Notes},
  volume={30},
  number={5},
  pages={306--315},
  year={2005},
  organization={ACM}
}

@inproceedings{Livshits:2005,
  title={DynaMine: finding common error patterns by mining software revision histories},
  author={Livshits, Benjamin and Zimmermann, Thomas},
  booktitle={ACM SIGSOFT Software Engineering Notes},
  volume={30},
  number={5},
  pages={296--305},
  year={2005},
  organization={ACM}
}

@article{Fowkes:2015,
  title={A Bayesian Network Model for Interesting Itemsets},
  author={Fowkes, Jaroslav and Sutton, Charles},
  journal={arXiv preprint arXiv:1510.04130},
  year={2015}
}

@inproceedings{Pang:2006,
  title={Introduction to data mining},
  author={Pang-Ning, Tan and Steinbach, Michael and Kumar, Vipin and others},
  booktitle={Library of congress},
  volume={74},
  year={2006}
}

@inproceedings{Yan:2002,
  title={gspan: Graph-based substructure pattern mining},
  author={Yan, Xifeng and Han, Jiawei},
  booktitle={Data Mining, 2002. ICDM 2003. Proceedings. 2002 IEEE International Conference on},
  pages={721--724},
  year={2002},
  organization={IEEE}
}

@inproceedings{Huan:2004,
  title={Spin: mining maximal frequent subgraphs from graph databases},
  author={Huan, Jun and Wang, Wei and Prins, Jan and Yang, Jiong},
  booktitle={Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining},
  pages={581--586},
  year={2004},
  organization={ACM}
}

@article{Kenji:2004,
  title={Efficient substructure discovery from large semi-structured data},
  author={Kenji, ABE and Kawasoe, Shinji and Sakamoto, Hiroshi and Arimura, Hiroki and Arikawa, Setsuo},
  journal={IEICE TRANSACTIONS on Information and Systems},
  volume={87},
  number={12},
  pages={2754--2763},
  year={2004},
  publisher={The Institute of Electronics, Information and Communication Engineers}
}

@inproceedings{Chi:2004,
  title={Cmtreeminer: Mining both closed and maximal frequent subtrees},
  author={Chi, Yun and Yang, Yirong and Xia, Yi and Muntz, Richard R},
  booktitle={Pacific-Asia Conference on Knowledge Discovery and Data Mining},
  pages={63--73},
  year={2004},
  organization={Springer}
}

@book{Han:2011,
  title={Data mining: concepts and techniques},
  author={Han, Jiawei and Pei, Jian and Kamber, Micheline},
  year={2011},
  publisher={Elsevier}
}

@inproceedings{Montandon:2013,
  title={Documenting APIs with examples: Lessons learned with the APIMiner platform.},
  author={Montandon, Jo{\~a}o Eduardo and Borges, Hudson and Felix, Daniel and Valente, Marco Tulio},
  booktitle={WCRE},
  pages={401--408},
  year={2013},
  organization={Citeseer}
}

@article{Kim:2013,
  title={Enriching documents with examples: A corpus mining approach},
  author={Kim, Jinhan and Lee, Sanghoon and Hwang, Seung-Won and Kim, Sunghun},
  journal={ACM Transactions on Information Systems (TOIS)},
  volume={31},
  number={1},
  pages={1},
  year={2013},
  publisher={ACM}
}

@inproceedings{Buse:2012,
  title={Synthesizing API usage examples},
  author={Buse, Raymond PL and Weimer, Westley},
  booktitle={2012 34th International Conference on Software Engineering (ICSE)},
  pages={782--792},
  year={2012},
  organization={IEEE}
}

@article{Ramanujam:2016,
  title={An Automatic Multidocument Text Summarization Approach Based on Na{\"\i}ve Bayesian Classifier Using Timestamp Strategy},
  author={Ramanujam, Nedunchelian and Kaliappan, Manivannan},
  journal={The Scientific World Journal},
  volume={2016},
  year={2016},
  publisher={Hindawi Publishing Corporation}
}

@inproceedings{Nasehi:2012,
  title={What makes a good code example?: A study of programming Q\&A in StackOverflow},
  author={Nasehi, Seyed Mehdi and Sillito, Jonathan and Maurer, Frank and Burns, Chris},
  booktitle={Software Maintenance (ICSM), 2012 28th IEEE International Conference on},
  pages={25--34},
  year={2012},
  organization={IEEE}
}

@inproceedings{Ying:2013,
  title={Code fragment summarization},
  author={Ying, Annie TT and Robillard, Martin P},
  booktitle={Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering},
  pages={655--658},
  year={2013},
  organization={ACM}
}

@inproceedings{Ying:2014,
  title={Selection and presentation practices for code example summarization},
  author={Ying, Annie TT and Robillard, Martin P},
  booktitle={Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering},
  pages={460--471},
  year={2014},
  organization={ACM}
}

@inproceedings{Arthur:2007,
  title={k-means++: The advantages of careful seeding},
  author={Arthur, David and Vassilvitskii, Sergei},
  booktitle={Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms},
  pages={1027--1035},
  year={2007},
  organization={Society for Industrial and Applied Mathematics}
}

@inproceedings{Xie:2006,
  title={MAPO: Mining API usages from open source repositories},
  author={Xie, Tao and Pei, Jian},
  booktitle={Proceedings of the 2006 international workshop on Mining software repositories},
  pages={54--57},
  year={2006},
  organization={ACM}
}

@incollection{Zhong:2009,
  title={MAPO: Mining and recommending API usage patterns},
  author={Zhong, Hao and Xie, Tao and Zhang, Lu and Pei, Jian and Mei, Hong},
  booktitle={ECOOP 2009--Object-Oriented Programming},
  pages={318--343},
  year={2009},
  publisher={Springer}
}

@inproceedings{Ayres:2002,
  title={Sequential pattern mining using a bitmap representation},
  author={Ayres, Jay and Flannick, Jason and Gehrke, Johannes and Yiu, Tomi},
  booktitle={Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining},
  pages={429--435},
  year={2002},
  organization={ACM}
}

@inproceedings{Wang:2013,
  title={Mining succinct and high-coverage API usage patterns from source code},
  author={Wang, Jue and Dang, Yingnong and Zhang, Hongyu and Chen, Kai and Xie, Tao and Zhang, Dongmei},
  booktitle={Proceedings of the 10th Working Conference on Mining Software Repositories},
  pages={319--328},
  year={2013},
  organization={IEEE Press}
}

@article{Fowkes2:2015,
  title={Parameter-Free Probabilistic API Mining at GitHub Scale},
  author={Fowkes, Jaroslav and Sutton, Charles},
  journal={arXiv preprint arXiv:1512.05558},
  year={2015}
}

@inproceedings{Kim:2009,
  title={Adding examples into java documents},
  author={Kim, Jinhan and Lee, Sanghoon and Hwang, Seung-won and Kim, Sunghun},
  booktitle={Automated Software Engineering, 2009. ASE'09. 24th IEEE/ACM International Conference on},
  pages={540--544},
  year={2009},
  organization={IEEE}
}

@inproceedings{Κim:2010,
  title={Towards an Intelligent Code Search Engine.},
  author={Kim, Jinhan and Lee, Sanghoon and Hwang, Seung-won and Kim, Sunghun},
  booktitle={AAAI},
  year={2010}
}

@inproceedings{Jiang:2007,
  title={Deckard: Scalable and accurate tree-based detection of code clones},
  author={Jiang, Lingxiao and Misherghi, Ghassan and Su, Zhendong and Glondu, Stephane},
  booktitle={Proceedings of the 29th international conference on Software Engineering},
  pages={96--105},
  year={2007},
  organization={IEEE Computer Society}
}

@inproceedings{Wang:2011,
  title={APIExample: An effective web search based usage example recommendation system for Java APIs},
  author={Wang, Lijie and Fang, Lu and Wang, Leye and Li, Ge and Xie, Bing and Yang, Fuqing},
  booktitle={Proceedings of the 2011 26th IEEE/ACM International Conference on Automated Software Engineering},
  pages={592--595},
  year={2011},
  organization={IEEE Computer Society}
}

@MastersThesis{Borges:2014,
    author={Hudson Silva Borges},
    title={{Extracting examples for API usage patterns}},
    school={Federal University of Minas Gerais},
    address={Brazil},
    year={2014},
}

@inproceedings{Weiser:1981,
  title={Program slicing},
  author={Weiser, Mark},
  booktitle={Proceedings of the 5th international conference on Software engineering},
  pages={439--449},
  year={1981},
  organization={IEEE Press}
}

@inproceedings{Allamanis:2013,
	author={Allamanis, Miltiadis and Sutton, Charles},
	title={{Mining Source Code Repositories at Massive Scale using Language Modeling}},
	booktitle={The 10th Working Conference on Mining Software Repositories},	
	year={2013},
	pages={207--216},
	organization={IEEE}
}

@inproceedings{Campello:2013,
  title={Density-based clustering based on hierarchical density estimates},
  author={Campello, Ricardo JGB and Moulavi, Davoud and Sander, J{\"o}rg},
  booktitle={Pacific-Asia Conference on Knowledge Discovery and Data Mining},
  pages={160--172},
  year={2013},
  organization={Springer}
}

@techreport{Bauckhage:2015,
  title={Numpy/scipy Recipes for Data Science: k-Medoids Clustering},
  author={Bauckhage, Christian},
  year={2015},
  institution={Technical Report, University of Bonn}
}

@article{Pawlik:2015,
  title={Efficient computation of the tree edit distance},
  author={Pawlik, Mateusz and Augsten, Nikolaus},
  journal={ACM Transactions on Database Systems (TODS)},
  volume={40},
  number={1},
  pages={3},
  year={2015},
  publisher={ACM}
}

@article{Pawlik:2016,
  title={Tree edit distance: Robust and memory-efficient},
  author={Pawlik, Mateusz and Augsten, Nikolaus},
  journal={Information Systems},
  volume={56},
  pages={157--173},
  year={2016},
  publisher={Elsevier}
}

@article{Tai:1979,
  title={The tree-to-tree correction problem},
  author={Tai, Kuo-Chung},
  journal={Journal of the ACM (JACM)},
  volume={26},
  number={3},
  pages={422--433},
  year={1979},
  publisher={ACM}
}

@article{Aliguliyev:2010,
  title={Clustering Techniques and Discrete Particle Swarm Optimization Algorithm for Multi-Document Summarization},
  author={Aliguliyev, Ramiz M},
  journal={Computational Intelligence},
  volume={26},
  number={4},
  pages={420--448},
  year={2010},
  publisher={Wiley Online Library}
}

@inproceedings{Wang:2008,
  title={Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization},
  author={Wang, Dingding and Li, Tao and Zhu, Shenghuo and Ding, Chris},
  booktitle={Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval},
  pages={307--314},
  year={2008},
  organization={ACM}
}

@inproceedings{Buse:2008,
  title={A metric for software readability},
  author={Buse, Raymond PL and Weimer, Westley R},
  booktitle={Proceedings of the 2008 international symposium on Software testing and analysis},
  pages={121--130},
  year={2008},
  organization={ACM}
}

@inproceedings{Winter:2013,
  title={Path-sensitive data flow analysis simplified},
  author={Winter, Kirsten and Zhang, Chenyi and Hayes, Ian J and Keynes, Nathan and Cifuentes, Cristina and Li, Lian},
  booktitle={International Conference on Formal Engineering Methods},
  pages={415--430},
  year={2013},
  organization={Springer}
}

@article{Maaten:2008,
  title={Visualizing data using t-SNE},
  author={Maaten, Laurens van der and Hinton, Geoffrey},
  journal={Journal of Machine Learning Research},
  volume={9},
  number={Nov},
  pages={2579--2605},
  year={2008}
}

@article{Young:2005,
  title={Software Testing and Analysis: Process, Principles and Techniques},
  author={Young, Michal and Pezze, Mauro},
  year={2005},
  publisher={John Wiley \& Sons}
}

@article{Manning:2008,
  title={Evaluation in information retrieval},
  author={Manning, Christopher D and Raghavan, Prabhakar and Sch{\"u}tze, Hinrich},
  journal={Introduction to information retrieval},
  pages={151--175},
  year={2008}
}

@inproceedings{Radevski:2016,
  title={Towards Building API Usage Example Metrics},
  author={Radevski, Stevche and Hata, Hideaki and Matsumoto, Kenichi},
  booktitle={2016 IEEE 23rd International Conference on Software Analysis, Evolution, and Reengineering (SANER)},
  volume={1},
  pages={619--623},
  year={2016},
  organization={IEEE}
}

@inproceedings{Demeyer:2013,
  title={Happy birthday! a trend analysis on past MSR papers},
  author={Demeyer, Serge and Murgia, Alessandro and Wyckmans, Kevin and Lamkanfi, Ahmed},
  booktitle={Proceedings of the 10th Working Conference on Mining Software Repositories},
  pages={353--362},
  year={2013},
  organization={IEEE Press}
}

@inproceedings{Hassan:2008,
  title={The road ahead for mining software repositories},
  author={Hassan, Ahmed E},
  booktitle={Frontiers of Software Maintenance, 2008. FoSM 2008.},
  pages={48--57},
  year={2008},
  organization={IEEE}
}

@article{Kagdi:2007,
  title={A survey and taxonomy of approaches for mining software repositories in the context of software evolution},
  author={Kagdi, Huzefa and Collard, Michael L and Maletic, Jonathan I},
  journal={Journal of software maintenance and evolution: Research and practice},
  volume={19},
  number={2},
  pages={77--131},
  year={2007},
  publisher={Wiley Online Library}
}

@article{Tan:2005,
  title={Chapter 6. association analysis: Basic concepts and algorithms},
  author={Tan, Pang-Ning and Michael, Steinbach and Kumar, Vipin},
  journal={Introduction to Data Mining. Addison-Wesley. ISBN},
  volume={321321367},
  year={2005}
}

@article{Chi:2005,
  title={Frequent subtree mining--an overview},
  author={Chi, Yun and Muntz, Richard R and Nijssen, Siegfried and Kok, Joost N},
  journal={Fundamenta Informaticae},
  volume={66},
  number={1-2},
  pages={161--198},
  year={2005},
  publisher={Ios press}
}

@inproceedings{Boros:2001,
  title={A clustering based approach to creating multi-document summaries},
  author={Boros, Endre and Kantor, Paul B and Neu, David J},
  booktitle={Proceedings of the 24th annual international ACM SIGIR conference on research and development in information retrieval},
  year={2001}
}

@inproceedings{Liu:2012,
  title={Query-Oriented Multi-Document Summarization via Unsupervised Deep Learning.},
  author={Liu, Yan and Zhong, Sheng-hua and Li, Wenjie},
  booktitle={AAAI},
  year={2012}
}