Robust classifiers without robust features
Neural Computation
Automated analysis of requirement specifications
ICSE '97 Proceedings of the 19th international conference on Software engineering
Extreme programming explained: embrace change
Extreme programming explained: embrace change
A vector space model for automatic indexing
Communications of the ACM
Feature Selection for Knowledge Discovery and Data Mining
Feature Selection for Knowledge Discovery and Data Mining
Connectionism and the Mind; An Introduction to Parallel Processing in Networks
Connectionism and the Mind; An Introduction to Parallel Processing in Networks
Design of an optimal nearest neighbor classifier using an intelligent genetic algorithm
Pattern Recognition Letters
METRICS '01 Proceedings of the 7th International Symposium on Software Metrics
Representation and Learning in Information Retrieval
Representation and Learning in Information Retrieval
Agile Project Management With Scrum
Agile Project Management With Scrum
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hierarchical Density-Based Clustering of Uncertain Data
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Proceedings of the 28th international conference on Software engineering
Object-Oriented Software Engineering: Using UML, Patterns and Java, Second Edition
Object-Oriented Software Engineering: Using UML, Patterns and Java, Second Edition
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
ICGSE '07 Proceedings of the International Conference on Global Software Engineering
Towards software configuration management for unified models
Proceedings of the 2008 international workshop on Comparison and versioning of software models
Questions, options, and criteria: elements of design space analysis
Human-Computer Interaction
Towards automation of iteration planning
Proceedings of the 24th ACM SIGPLAN conference companion on Object oriented programming systems languages and applications
On improving application utility prediction
CHI '10 Extended Abstracts on Human Factors in Computing Systems
The CLOTHO project: predicting application utility
Proceedings of the 8th ACM Conference on Designing Interactive Systems
Hi-index | 0.00 |
Categorizing software engineering artifacts, tasks in our case, is often a prerequisite for analysis and research. As an example, categorizing tasks according to their activity allows for a post-mortem analysis of the life cycle model of a project and can be used as a foundation for software metrics. Many categorical attributes of software artifacts are often not entered correctly or are not entered at all. For example, we observed a significant number of obsolete tasks that were not categorized as such. In this paper, we present an approach for the automatic classification of tasks in software development projects using machine learning. We evaluated our technique by two sample applications from the domain of project management: Tasks are classified according to activity and relevance, respectively. Project-relevant characteristics are learned by the classifier from the project history. Five-fold cross-validation of both applications resulted in classification accuracies of 80.51% (six categories) and 83.72% (two categories). Our approach is also applicable to other types of artifacts and categorizations within a unified software engineering model.