02070nas a2200277   4500000000100000000000100001008004100002260001200043653002300055653001200078653002500090653002300115653001500138653003300153100001500186700001800201700001600219700001400235700001400249245017900263856005800442300001100500490000600511520126100517022001401778       2024                            d  c12/202410aAcademic Analytics10aDropout10aStudents Interaction10aLearning Analytics10aPrediction10aIntelligent Tutoring Systems1 aA. Llauró1 aDavid Fonseca1 aE. Villegas1 aM. Aláez1 aS. Romero00aImprovement of Academic Analytics Processes Through the Identification of the Main Variables Affecting Early Dropout of First-Year Students in Technical Degrees. A Case Study  uhttps://www.ijimai.org/journal/bibcite/reference/3330  a92-1030 v93 aThe field of research on the phenomenon of university dropout and the factors that promote it is of the utmost relevance, especially in the current context of the Covid-19 pandemic. Students who have started degrees in the last two years have completed their university studies in periods of lockdown and unlike traditional education, this has often involved taking online classes. In this scenario, the students' motivation and the way they are able to cope with the difficulties of the first year of a university course are very relevant, especially in technical degrees. Previous studies show that a large number of undergraduate students drop out prematurely. In order to act to reduce dropout rates, schools, especially technical schools, should be able to map the entry profile of students and identify the factors that promote early dropout. This paper focuses on identifying, categorizing and evaluating a number of indicators according to the perception of tutors and the field of study, based on the application of quantitative and qualitative techniques. The results support the approach taken, as they show how tutors can identify students at risk of dropping out at the beginning of the course and act proactively to monitor and motivate them.  a1989-1660