Keywords extraction in text using complex networks

• Grant number: 17/18126-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2017
• End date: September 30, 2018
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Lilian Berton
• Grantee: Pedro Spoljaric Gomes
• Host Institution: Instituto de Ciência e Tecnologia (ICT). Universidade Federal de São Paulo (UNIFESP). Campus São José dos Campos. São José dos Campos , SP, Brazil

Abstract

Keywords are an important way to summarize documents, as well to facilitate a topic search. Only a small fraction of documents have keywords assigned by the author and execute this task manually in existing documents are a very laborious task. Therefore, it is highly desirable to automate the process of extracting keywords. Many methods require a number of labeled texts to train a classifier. In this work, we will explore unsupervised approaches, modeling texts as complex networks and extracting measures of centrality, moreover, we will apply random walk on the networks to identify the most important vertices, which could be keywords in a text document. (AU)