In this activity we are studying the paper by Dyckhoff et al. (2013)

“The authors include tables that focus on why learning analytics are used. Reflect on the questions asked by teachers (Table 1) and the goals of learning analytics (Table 4).

Note in your learning journal or blog which of these questions can be considered:

a.data driven

b.pedagogy driven.”

---

(A) Qualitative evaluation

• How do students like/rate/value specific learning offerings? (DATA DRIVEN – IF survey data is gathered)
• How difficult/easy is it to use the learning offering? (PEDAGOGY – learning design standards)
• Why do students appreciate the learning offering? (NEITHER – this is personal feelings of the student)

(B) Quantitative measures of use / attendance

• When and how long are student accessing specific learning offerings (during a day)? (DATA DRIVEN)
• How often do students use a learning environment (per week)? (DATA DRIVEN)
• Are there specific learning offerings that are NOT used at all? (DATA DRIVEN)

(C) Differentiation between groups of students

• By which properties can students be grouped? (DATA DRIVEN – from profile data)
• Do native speakers have fewer problems with learning offerings than non-native speakers? (NEITHER – would need to relate first language to reported problems)
• How is the acceptance of specific learning offerings differing according to user properties (e.g. previous knowledge)? (NEITHER – personal preferences again)

(D) Differentiation between learning offerings

• Are students using specific learning materials (e.g. lecture recordings) in addition or alternatively to attendance? (DATA DRIVEN – if attendance data was correlated with online use)
• Will the access of specific learning offerings increase if lectures and exercises on the same topic are scheduled during the same week? (DATA DRIVEN – again could be ascertained from log data and test dates)

(E) Data consolidation / Correlation

• How many (percent of the) learning modules are student viewing? (DATA DRIVEN)
• Which didactical activities facilitate continuous learning? (PEDAGOGY – would need to be reported over a long period of time)
• How do learning offerings have to be provided and combined to with support to increase usage? (Could be both – data provides evidence of increased usage then historical link with learning offering through each iteration)

(F) Effects on Performance

• How do those low achieving students profit by continuous learning with e- test compared to those who have not yet used the e-tests? (Could fit both categories again. Data informing continuous e-test results of low achieving students vs. Control group)
• Is the performance in e-tests somehow related to exam grades? (DATA driven)

It is necessary to consider a third classifier where an analytic metric is neither data driven nor pedadogical. I think this third classifier is based on internalised information which cannot be gathered from a data source. Perhaps “Ex machina”.

 

---

References:

Dyckhoff, A.L., Lukarov, V., Muslim, A., Chatti, M.A. and Schroeder, U., 2013, April. Supporting action research with learning analytics. In Proceedings of the Third International Conference on Learning Analytics and Knowledge (pp. 220-229).