Learning Analytics techniques are widely used to improve students' performance. Data collected from students' assessments are helpful to predict their success and questionnaires are extensively adopted to assess students' knowledge. Several mathematical models studying the correlation between students' extit{hidden skills} and their performance to questionnaires' items have been introduced. Among them, Non-negative matrix factorizations (NMFs) have been proven to be effective in automatically extracting hidden skills, a time-consuming activity that is usually tackled manually prone to subjective interpretations. In this paper, we present an intelligent data analysis approach based upon NMF. Data are collected from a competition, namely emph{MathsChallenge}, performed by the University of Foggia. In 2021 the competition has been held, for the first time, online due to the Covid-19 pandemic.
Intelligent Knowledge Understanding from Students Questionnaires: A Case Study
Luca Grilli;Alfonso Guarino;
2022-01-01
Abstract
Learning Analytics techniques are widely used to improve students' performance. Data collected from students' assessments are helpful to predict their success and questionnaires are extensively adopted to assess students' knowledge. Several mathematical models studying the correlation between students' extit{hidden skills} and their performance to questionnaires' items have been introduced. Among them, Non-negative matrix factorizations (NMFs) have been proven to be effective in automatically extracting hidden skills, a time-consuming activity that is usually tackled manually prone to subjective interpretations. In this paper, we present an intelligent data analysis approach based upon NMF. Data are collected from a competition, namely emph{MathsChallenge}, performed by the University of Foggia. In 2021 the competition has been held, for the first time, online due to the Covid-19 pandemic.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
