Table 2 Coding scheme to analyze included publications
Category | Code | Label | Description |
|---|---|---|---|
Type of data (what) | Type of data | A1 | Refers to any kind of data such as academic data, performance data, interaction data, etc. that are collected by tutoring to support feedback practices in education |
Methods (how) | Machine learning | B1 | Refers to the machine learning methods such as neural network to learn from data and perform tasks within tutoring systems |
Data mining | B2 | Refers to the data mining methods such as clustering, classification, decision tree, regression, etc. that are used to analyze data within tutoring systems | |
Gaming | B3 | Refers to the leveraging gaming methods within tutoring systems | |
Others | B4 | Refers to the other methods such home grown systems | |
Objectives (why) | Monitoring | C1 | Refers to tracking students’ learning performance |
Prediction | C2 | Refers to predicting students’ learning behavior and performance | |
Assessment | C3 | Refers to providing an evidence-based assessment | |
Adaptation | C4 | Refers to providing an adaptive and flexible learning scenario | |
Personalization | C5 | Refers to providing individualized training scenarios | |
Recommendation | C6 | Refers to providing recommendation of what to do next | |
Others | C7 | Refers to any other goal that can help to support learners | |
Target Learners and stakeholders (who) | Elementary | D1 | Refers to the elementary school students as the learners |
High school | D2 | Refers to the high school students as the learners | |
University | D3 | Refers to the university students as the learners | |
Others | D4 | Refers to not specifically mentioned who is the learners |