Abstract
The idea of automating systematic reviews has been motivated by both advances in technology that have increased the availability of full-text scientific articles and by sociological changes that have increased the adoption of evidence-based medicine. Although much work has focused on automating the information retrieval step of the systematic review process with a few exceptions the information extraction and analysis have been largely overlooked. In particular, there is a lack of systems that automatically identify the results of an empirical study. Our goal in this paper is to fill that gap. We frame the problem as a classification task and employ three different objective, domain-independent feature selection strategies and two different classifiers. Additionally, special attention is paid to the selection of the data set used in this experiment, the feature selection metrics as well as the classification algorithms, and parameters of the algorithms used for classification in order to show the situatedness of this experiment and its dependence on each of the three parameters.
| Original language | English (US) |
|---|---|
| Title of host publication | iConference 2015 Proceedings |
| Publisher | iSchools |
| State | Published - Mar 15 2015 |
Keywords
- machine learning
- classification
- scientific results
- systematic reviews
- text categorization
- feature selection