A model to summarize user action log files

Social networks, web portals or e-learning platforms producein general a large amount of data everyday, normally stored in its rawformat in log file systems and databases. Such data can be condensedand summarized to improve reporting performance and reduce the system load. This data summarization reduces the amount of space that isrequired to store software data but produces, as a side effect, a decreaseof their informative capability due to an information loss. In this workwe study the problem of summarizing data obtained by the log systemsof chronology-dependent applications with a lot of users. In particular,we present a method to reduce the data size, collapsing the descriptionsof more events in a unique descriptor or in a smaller set of descriptorsand pose the optimal summarization problem.