Towards Constructing a Corpus for Studying the Effects of Treatments and Substances Reported in PubMed Abstracts
This work addresses the problem of extracting effect information from medical literature for researchers, but it is incremental as it builds on existing methods for corpus creation and classification.
The authors constructed an annotated corpus of 750 PubMed abstracts to study effects of treatments or substances, aiming to train a text classifier that currently achieves 78.80% accuracy.
We present the construction of an annotated corpus of PubMed abstracts reporting about positive, negative or neutral effects of treatments or substances. Our ultimate goal is to annotate one sentence (rationale) for each abstract and to use this resource as a training set for text classification of effects discussed in PubMed abstracts. Currently, the corpus consists of 750 abstracts. We describe the automatic processing that supports the corpus construction, the manual annotation activities and some features of the medical language in the abstracts selected for the annotated corpus. It turns out that recognizing the terminology and the abbreviations is key for determining the rationale sentence. The corpus will be applied to improve our classifier, which currently has accuracy of 78.80% achieved with normalization of the abstract terms based on UMLS concepts from specific semantic groups and an SVM with a linear kernel. Finally, we discuss some other possible applications of this corpus.