Dogaru, TeodoraGötze, NoraRotelli, DanielaBerendsohn, YoelMerceron, AgatheSauer, PetraRöpke, RenéSchroeder, Ulrik2023-08-302023-08-302023978-3-88579-732-6https://dl.gi.de/handle/20.500.12116/42235Analysing Learning Management System (LMS) log data gives insight into student learning behaviour that can help to predict performance, and as a consequence to avoid drop-out. This contribution provides an application and an adaptation of Rotelli and Monreale’s methodology [RM22] for defining tasks in a set of 10,532 online courses collected from seven universities. Unlike [RM22], we access the log data directly from the Moodle database. Even though our data set is much bigger and more heterogeneous than the one described in [RM22], we could adapt the data selection and filtering, as well as the components’ redefinition and alignment and employ their methodology to define tasks. This work is a contribution to make log data preprocessing open, replicable and more transparent.enLMSMoodle log data analysisData preprocessingText/Conference Paper10.18420/delfi2023-711617-5468