publications:
- title: "Empirical language analysis in software linguistics"
  author:
  - name: "Jean-Marie Favre"
    link: "http://megaplanet.org/jean-marie-favre/"
  - name: "Dragan Gasevic"
    link: "http://www.sfu.ca/~dgasevic/"
  - name: "Ralf Lämmel"
    link: "http://www.uni-koblenz.de/~laemmel/Site/Home.html"
  - name: "Ekaterina Pek"
    link: "http://www.uni-koblenz.de/~pek/"
  year: "2011"
  abstract: "Software linguistics is the science of software languages. In this short paper, we sketch the general discipline of software linguistics, but our focus is on one part of it: empirical analysis of software languages. Such analysis is concerned with understanding language usage on the grounds of a corpus. In this short paper, we sketch a survey on empirical language analysis, and we argue that the research method of content analysis is needed for a thorough survey."
  note: "10 pages. Post-proceedings to appear."
  tags:
  - "empirical"
  - "analysis"
  - "survey"
  - "e-science"
  researchr: "https://researchr.org/publication/FavreEtAl11"
  cites: 0
  citedby: 0
  booktitle: "SLE '10: Post-proceedings of the 2010 3rd International Conference on Software Language Engineering"
  series: "LNCS"
  publisher: "Springer"
  kind: "inproceedings"
  key: "FavreEtAl11"
- title: "Towards Privacy Policy-Aware Web-Based Systems"
  author:
  - name: "Ekaterina Pek"
    link: "http://www.uni-koblenz.de/~pek/"
  year: "2010"
  tags:
  - "rule-based"
  - "context-aware"
  researchr: "https://researchr.org/publication/Pek10"
  cites: 0
  citedby: 0
  booktitle: "SLE-DS '10: Proceedings of the 2010 1st Doctoral Symposium of the International Conference on Software La nguage Engineering"
  kind: "inproceedings"
  key: "Pek10"
- title: "Large-scale, AST-based API-usage analysis of open-source Java projects"
  author:
  - name: "Ralf Lämmel"
    link: "http://www.uni-koblenz.de/~laemmel/Site/Home.html"
  - name: "Ekaterina Pek"
    link: "http://www.uni-koblenz.de/~pek/"
  - name: "Jürgen Starek"
    link: "https://researchr.org/alias/j%C3%BCrgen-starek"
  year: "2011"
  abstract: "Research on API migration and language conversion relies on empirical data about API usage for the benefit of validating mapping rules for API migration in terms of prioritization, applicability, generality, and correctness. We describe an approach to large-scale API-usage analysis of open-source Java projects, which we also instantiate for the SourceForge open-source repository in a certain way. Our approach covers checkout, building, tagging with metadata, fact extraction, analysis, and synthesis with a large degree of automation. Fact extraction relies on resolved (type-checked) ASTs. We describe a few specific forms of API-usage analysis; they are motivated by API migration. These forms are concerned with analysing API footprint (such as the number of distinct APIs used in a project), API coverage (such as the percentage of methods of an API used in a corpus), and framework-like vs. class-library-like usage.  "
  tags:
  - "empirical"
  - "data validation"
  - "rule-based"
  - "Java"
  - "data-flow language"
  - "tagging"
  - "points-to analysis"
  - "analysis"
  - "data-flow"
  - "source-to-source"
  - "rules"
  - "migration"
  - "data-flow analysis"
  - "coverage"
  - "systematic-approach"
  - "open-source"
  researchr: "https://researchr.org/publication/LaemmelPS11"
  cites: 0
  citedby: 0
  booktitle: "SAC '11: Proceedings of the 26th ACM Symposium on Applied Computing"
  kind: "inproceedings"
  key: "LaemmelPS11"
- title: "Vivisection of a Non-Executable, Domain-Specific Language - Understanding (the Usage of) the P3P Language"
  author:
  - name: "Ralf Lämmel"
    link: "http://www.uni-koblenz.de/~laemmel/Site/Home.html"
  - name: "Ekaterina Pek"
    link: "http://www.uni-koblenz.de/~pek/"
  year: "2010"
  doi: "http://dx.doi.org/10.1109/ICPC.2010.45"
  abstract: "P3P is the policy language with which websites declare the intended use of data that is collected about users of the site. We have systematically collected P3P-based privacy policies from websites listed in the Google directory, and analysed the resulting corpus with regard to different levels of validity, size or complexity metrics, different cloning levels, coverage of language constructs, and the use of the language’s extension mechanism. In this manner, we have found interesting characteristics of P3P in the wild. For instance, cloning is exceptionally common in this domain, and encountered language extensions exceed the base language in terms of grammar complexity. Overall, this effort helps understanding the de-facto usage of the non-executable, domain-specific language P3P. Some elements of our methodology may be useful for other software languages as well.  "
  links:
    doi: "http://dx.doi.org/10.1109/ICPC.2010.45"
  tags:
  - "rule-based"
  - "data-flow language"
  - "data-flow"
  - "Google"
  - "coverage"
  - "systematic-approach"
  - "grammar"
  - "domain-specific language"
  researchr: "https://researchr.org/publication/LaemmelP10"
  cites: 0
  citedby: 0
  booktitle: "ICPC '10: Proceedings of the 2010 IEEE 18th International Conference on Program Comprehension"
  address: "Braga, Minho, Portugal"
  publisher: "IEEE Computer Society"
  isbn: "978-0-7695-4113-6"
  kind: "inproceedings"
  key: "LaemmelP10"