2015
Arnaoudova, Venera; Haiduc, Sonia; Marcus, Andrian; Antoniol, Giuliano
The Use of Text Retrieval and Natural Language Processing in Software Engineering Proceedings Article
In: Proceedings of the International Conference on Software Engineering (ICSE) - Technical Briefings, pp. 949–950, 2015.
BibTeX | Tags: information retrieval, natural language processing
@inproceedings{Arnaoudova-icseTB15-NLPinSE,
title = {The Use of Text Retrieval and Natural Language Processing in Software Engineering},
author = {Venera Arnaoudova and Sonia Haiduc and Andrian Marcus and Giuliano Antoniol},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the International Conference on Software Engineering (ICSE) - Technical Briefings},
pages = {949--950},
keywords = {information retrieval, natural language processing},
pubstate = {published},
tppubtype = {inproceedings}
}
2014
Medini, Soumaya; Arnaoudova, Venera; Penta, Massimiliano Di; Antoniol, Giuliano; Guéhéneuc, Yann-Gaël; Tonella, Paolo
SCAN: An Approach to Label and Relate Execution Trace Segments Journal Article
In: Journal of Software: Evolution and Process (JSEP), vol. 26, no. 11, pp. 962–995, 2014.
Abstract | BibTeX | Tags: concept identification, dynamic analysis, empirical study, formal concept analysis, information retrieval
@article{SCAN-14,
title = {SCAN: An Approach to Label and Relate Execution Trace Segments},
author = {Soumaya Medini and Venera Arnaoudova and Massimiliano {Di Penta} and Giuliano Antoniol and Yann-Gaël Guéhéneuc and Paolo Tonella},
year = {2014},
date = {2014-01-01},
journal = {Journal of Software: Evolution and Process (JSEP)},
volume = {26},
number = {11},
pages = {962--995},
abstract = {Program comprehension is a prerequisite to any maintenance and evolution task. In particular, when performing feature location, developers perform program comprehension by abstracting software features and identifying the links between high-level abstractions (features) and program elements.
We present Segment Concept AssigNer (SCAN), an approach to support developers in feature location. SCAN uses a search-based approach to split execution traces into cohesive segments. Then, it labels the segments with relevant keywords and, finally, uses formal concept analysis to identify relations among segments. In a first study, we evaluate the performances of SCAN on six Java programs by 31 participants. We report an average precision of 69% and a recall of 63% when comparing the manual and automatic labels and a precision of 63% regarding the relations among segments identified by SCAN. After that, we evaluate the usefulness of SCAN for the purpose of feature location on two Java programs. We provide evidence that SCAN (i) identifies 69% of the gold set methods and (ii) is effective in reducing the quantity of information that developers must process to locate features—reducing the number of methods to understand by an average of 43% compared to the entire execution traces.},
keywords = {concept identification, dynamic analysis, empirical study, formal concept analysis, information retrieval},
pubstate = {published},
tppubtype = {article}
}
We present Segment Concept AssigNer (SCAN), an approach to support developers in feature location. SCAN uses a search-based approach to split execution traces into cohesive segments. Then, it labels the segments with relevant keywords and, finally, uses formal concept analysis to identify relations among segments. In a first study, we evaluate the performances of SCAN on six Java programs by 31 participants. We report an average precision of 69% and a recall of 63% when comparing the manual and automatic labels and a precision of 63% regarding the relations among segments identified by SCAN. After that, we evaluate the usefulness of SCAN for the purpose of feature location on two Java programs. We provide evidence that SCAN (i) identifies 69% of the gold set methods and (ii) is effective in reducing the quantity of information that developers must process to locate features—reducing the number of methods to understand by an average of 43% compared to the entire execution traces.
2010
Arnaoudova, Venera; Eshkevari, Laleh Mousavi; Oliveto, Rocco; Guéhéneuc, Yann-Gaël; Antoniol, Giuliano
Physical and Conceptual Identifier Dispersion: Measures and Relation to Fault Proneness Technical Report
École Polytechnique de Montréal no. EPM-RT-2010-02, 2010.
BibTeX | Tags: entropy, fault models, information retrieval, program comprehension, source code identifiers
@techreport{2010-Polytechnique-Arnaoudova-IdentifierDispersion,
title = {Physical and Conceptual Identifier Dispersion: Measures and Relation to Fault Proneness},
author = {Venera Arnaoudova and Laleh {Mousavi Eshkevari} and Rocco Oliveto and Yann-Gaël Guéhéneuc and Giuliano Antoniol},
year = {2010},
date = {2010-01-01},
number = {EPM-RT-2010-02},
institution = {École Polytechnique de Montréal},
keywords = {entropy, fault models, information retrieval, program comprehension, source code identifiers},
pubstate = {published},
tppubtype = {techreport}
}
Arnaoudova, Venera; Eshkevari, Laleh Mousavi; Oliveto, Rocco; Guéhéneuc, Yann-Gaël; Antoniol, Giuliano
Physical and Conceptual Identifier Dispersion: Measures and Relation to Fault Proneness Proceedings Article
In: Proceedings of the International Conference on Software Maintenance (ICSM) - ERA Track, pp. 1–5, 2010.
BibTeX | Tags: entropy, fault models, information retrieval, program comprehension, source code identifiers
@inproceedings{2010-ICSMera-Arnaoudova-IdentifierDispersion,
title = {Physical and Conceptual Identifier Dispersion: Measures and Relation to Fault Proneness},
author = {Venera Arnaoudova and Laleh {Mousavi Eshkevari} and Rocco Oliveto and Yann-Gaël Guéhéneuc and Giuliano Antoniol},
year = {2010},
date = {2010-01-01},
booktitle = {Proceedings of the International Conference on Software Maintenance (ICSM) - ERA Track},
pages = {1--5},
keywords = {entropy, fault models, information retrieval, program comprehension, source code identifiers},
pubstate = {published},
tppubtype = {inproceedings}
}