Abstract:
This research is to classify a research paper using keyword clustering. The objective is to reduce
the time consumption in manual classification of research papers. Classifying of a research paper
is achieved by introducing and automated way to generating keyword sections and finding the
respective domain. This takes away the need to scan the entire research. In other words, the manual
classification approach is succeeded using a keyword extraction model and an unsupervised
clustering model. This research is based on unsupervised learning and clustering model.
A comprehensive literature review and an online survey of knowledge resources were conducted
to gather requirements to design a solution. Natural language Processing and Machine Learning
are used in implementing the solution. Finally, the evaluation of the test results of the project show
the possibility that this novel approach can be used to automatically classify research papers. In
conclusion, this research makes a key note for identifying new approaches to keyword clustering
and extraction.
