To Enhance Full-Text Biomedical Document Classification Through Semantic Enrichment.

The rapid growth of the scientific literature makes text classification essential specially in the biomedical research domain to help researchers to focus on the latest findings in a fast and efficient way. The potential benefits of using text semantic enrichment to enhance the biomedical document classification is presented in this study. We show the importance of enriching the corpora with semantic information to improve the full-text classification. The approach involves the semantic enrichment of a Medline corpus with a Semantic Repository (SemRep) which extracts semantic predications from biomedical text. The study also addresses the problem of treating highly dimensional data while maintaining the semantic structure of the corpus. Experimental results lead to the sustained conclusion that better results are achieved with full-text instead of using only abstracts and titles. We also conclude that the application of enriched techniques to full-texts significantly improves the task of text classification providing a significant contribution for the biomedical text mining research.