Data Collection, Processing and Analysis

........refers to the measurement, collection, analysis, and reporting data about learners and their contexts, for purposes of understanding and optimising learning and the environments in which it occurs.

This is the ..... framework, which use the educational and psychological theory, together with the application of learning analytics to understand deeply learning processes.

Organize these examples of data collecting methods into the right categories

Groups:

(a) Tests, Text data

,

(b) Self-reports, video/audio data

,

(c) Biometric devices

,

(d) Digital traces

• Learner interactions

• Interaction time

• Heart rate variability

• Idle time

• Page visits

• Intelligence

• Eye tracker

• Knowledge

• Intrinsic motivation

• Click patterns

• Skills

• Self-efficacy

• Electrodermal activity

• Body posture

• Functional near-infrared spectroscopy

• Learner products

• Transcribed conservations

Order these data-collecting approaches into increasing degrees of obtrusiveness

• Digital traces

• Biometric devices

• Video and audio data

• Text data

• Tests, Self-reports

What can be the risks of collecting data from a single source or metric? (multiple answers)

• Missing data

• Elaborating signal-to-noise ratio

• Missing contextual information

• Increasing the probability to measure latent aspects

Data......provide the methodological link between collected data and their utilisation in adaptive learning systems

Match the following features to appropriate methods of data processing and analysis

• labeled + unlabelled data

• Reinforcing algorithms

• apply validated models

• Semi-supervised algorithms

• task-driven approach

• Unsupervised algorithms

• data-driven approach

• Supervised algorithm

• environment-driven approach

• Discovery with models

​ Organise these features in correct categories

Groups:

(a) Supervised algorithms

,

(b) Unsupervised algorithms

• clustering

• inputs and coresponding outputs

• classification

• association

• regression

• unlabelled data

Which algorithms should we use for this data set?

• Supervised algorithms

• Unsupervised algorithms

• None of them

• Both of them

Organise these approaches of data processing and analysis into the decreasing degree of interpretability

• Unsupervised algorithms

• Classical statistical method

• Supervised algorithms

• Visualization