Keine Notizen für die Folie
Microsoft Desirability Toolkit
‘Knowing about collaboration andcommunication’ (the 3rd row with *) is not addressed by SAM, but is added to check a possible bias. The highest rated was ‘knowing how much time students spent’ and ‘Awareness of what students are doing’ Finding students in trouble and the best students was also rated rather low. Awareness of resource use has been mostly met, but can be improved by differentiating external resources (the external resource use issue is indecisive).
Actual use was high
For this evaluation we wanted to get expert feedback and see how SAM would operate in a large course. SAM was deployed in an open onlinecourse on Learning and Knowledge Analytics (LAK)5 – an emerging research domain in TEL that focuses on better measurement, analysis, visualization and reporting of data about learners . More details on iteration 2 and 3 are available in . allow re-ordering of the axes through drag-and-drop for better metrics comparison. To cope with the line density better, configurable histograms (12) are added to the axes.270 participants
Providing feedback most importantBoth LAK and CGIAR teachers want to understand the document use. The main differences between LAK and CGIAR teachers are: LAK rates finding students at risk higher and finding good students lower, online tool use is not so interesting for LAK teachers and collaboration is more important. Awareness is also rated high. Comparing with the objectives, awareness and resource use is again the most important.
How can data sets be shared according to privacy and legal protection rights? How to develop a respective policy to use and share data sets? How to pre-process data sets to make them suitable for other researchers? How to define common evaluation criteria for TEL recommender systems? How to develop overview methods to monitor the performance of TEL recommender systems on data sets?