| Resumo: | Using data for making decisions is not new; companies use complex computations on customer data for business intelligence or analytics. Business intelligence techniques can discern historical patterns and trends from data and can create models that predict future trends and patterns. Analytics, broadly defined, comprises applied techniques from computer science, mathematics, and statistics for extracting usable information from very large datasets. Data itself is not new. Data has always been generated and used to inform decision-making. However, most of this was structured and organised, through regular data collections, surveys, etc. What is new, with the invention and dominance of the Internet and the expansion of digital systems across all sectors, is the amount of unstructured data we are generating. This is what we call the digital footprint: the traces that individuals leave behind as they interact with their increasingly digital world. Data analytics is the process where data is collected and analysed in order to identify patterns, make predictions, and inform business decisions. Our capacity to perform increasingly sophisticated analytics is changing the way we make predictions and decisions, with huge potential to improve competitive intelligence. These examples suggest that the actions from data mining and analytics are always automatic, but that is less often the case. Educational Data Mining (EDM) and Learning Analytics (LA) have the potential to make visible data that have heretofore gone unseen, unnoticed, and therefore unactionable. To help further the fields and gain value from their practical applications, the recommendations are that educators and administrators: • Develop a culture of using data for making instructional decisions; • Involve IT departments in planning for data collection and use; • Be smart data consumers who ask critical questions about commercial offerings and create demand for the most useful features and uses; • Start with focused areas where data will help, show success, and then expand to new areas; • Communicate with students and parents about where data come from and how the data are used; • Help align state policies with technical requirements for online learning systems. This report documents the first steps conducted within the SPEET1 ERASMUS+ project. It describes the conceptualization of a practical tool for the application of EDM/LA techniques to currently available academic data. The document is also intended to contextualise the use of Big Data within the academic sector, with special emphasis on the role that student profiles and student clustering do have in support tutoring actions. The report describes the promise of educational data mining (seeking patterns in data across many student actions), learning analytics (applying predictive models that provide actionable information), and visual data analytics (interactive displays of analyzed data) and how they might serve the future of personalized learning and the development and continuous improvement of adaptive systems. How might they operate in an adaptive learning system? What inputs and outputs are to be expected? In the next sections, these questions are addressed by giving a system-level view of how data mining and analytics could improve teaching and learning by creating feedback loops. Finally, the proposal of the key elements that conform a software application that is intended to give support to this academic data analysis is presented. Three different key elements are presented: data, algorithms and application architecture. From one side we should have a minimum data available. The corresponding relational data base structure is presented. This basic data can always be complemented with other available data that may help to decide or/and to explain decisions. Classification algorithms are reviewed and is presented how they can be used for the generation of the student clustering problem. A convenient software architecture will act as an umbrella that connects the previous two parts. The document is intended to be useful for a first understanding of academic data analysis. What we can get and what we do need to do. This is the first of a series of reports that taken all together will provide a complete and consistent view towards the inclusion of data mining as a helping hand in the tutoring action.
|
|---|