PROJECT TITLE :

Automatic algorithm to classify and locate research papers using natural language

ABSTRACT:

The objective of this paper was to produce an automatic engine to classify and find information using natural language. The proposal integrates a group of two algorithms to extract data from completely different repositories using their own open APIs and creates a information database employing a natural language approach employing a Bayesian algorithm to classify and a second algorithm to clean the paper. Putting said techniques together derived in a very robust alternative which reach common gaps in classification and site of data together with avoid the utilization of the whole paper to induce info and not only the knowledge introduced at the instant of upload the paper within the digital library. The proposal was oriented to classify and find research papers so as to higher describe this contribution, but, findings might be applicable to an unlimited vary of eventualities. An adaptation of the popular methodology Crisp-DM was used to guage the performance of the algorithm obtaining smart results in classifying, searching, and feeding the knowledge base.