Internet data extraction and analysis for profile generation

Abstract

Almost everything is stored on the Internet nowadays, and relying data on the Internet has become usual over the last years, directly increasing the value of data retrieval. Via Internet, data scientist can now find a way to access all the available data that is stored on the Internet, so they can turn that data into useful information. As people rely a lot of data on the Internet, they sometimes ignore the fact that all that data can be easily extracted, even when people think their information is safe or unavailable. In this article, we propose a system in where some data extraction techniques are going to be analysed in order to have an overview of the amount of data of a person that can be extracted from the Internet, and how that data is turned into information with an additional value in order to make data useful. The proposed system is going to be capable of retrieving huge loads of data from a person and process it using Artificial Intelligence, in order to classify its content to generate a personal profile containing all the information once its analysed. This research is based on personal profile generation of people from Spain, but it could be implemented for any other country. The proposed system has been implemented and tested on different people, and the results were quite satisfactory.