An Approach to Mine Textual Information From Pubmed Database

The web has greatly improved access to scientific literature. A wide spectrum of research data has been created and collected by researchers. However, textual information on the web are largely disorganized, with research articles being spread across archive sites, institution sites, journal sites and researcher homepages. Data was widely available over internet and many kinds of data pose the current challenge in storage and retrieval. Datasets can be made more accessible and user-friendly through annotation, aggregation, cross-linking to other datasets. Biomedical datasets are growing exponentially and new curative information appears regularly in research publications such as MedLine, PubMed, Science Direct etc. Therefore, a context based text mining was developed using python language to search huge database such as PubMed based on a given keyword which retrieves data between specified years.