Minería de Uso Web aplicada a los archivos logs del servidor Proxy de la UTPL, para obtener patrones de uso generales y específicos

Abstract

The present study explores and analyzes the log files of the UTPL proxy server to find hidden patterns and record the activity of users surfing the internet on the university campus. For this purpose, Data Mining is applied, which is the technology that allows us to discover hidden knowledge in any data repository, regardless of the type that these are. Web Mining is based on the same concept as Data Mining, with the great difference that is applied to data collected from the web; For this purpose, is divided into three areas of study Mining applied to the Content, Structure and Use of the Web. Specifically, Web Use Mining (WUM) allows us to find useful patterns of access to both a website and open services, such as the UTPL proxy server, which served as a study object for the present research work providing the Information recorded in the log files that are generated daily by the accesses of users who browse the web. For the present study several phases were developed, from the understanding of the technology, established objectives, methodology or architecture defined for the accomplishment of the Mining of Web Use. In itself, the state of the art that provided the bases and foundations for the successful realization of the project.