Learning Analytics – Our Services

Apply Learning Analytics on person and education data
a) How data is captured in learning experiences
b) Considering ethics and privacy issues
c) How to work as part of a team in a domain that is becoming increasingly cross-disciplinary

Apply Feature Engineering (to improve learning environments)
This process of building features will be applied within a broader data-intensive learning analytics (research) workflow. We will use strategies for using prior research, knowledge from practice, and logic to create features, as well as build and evaluate learning models.
Use data from digital learning environments and administrative data systems in a ‘feature engineering workflow’ to:
a) help better understand relevant learning environments
b) identify participants (students) in need of support
c) assess changes made to learning environments

Predictive Modeling in Learning Analytics: (Educational Predictive Models)
a) Apply feature selection to identify relevant attributes in the data
b) Analyze educational data and make predictions about participant (student) outcomes
i) Student success systems
ii) Early warning systems for at-risk learners
Learners are categorized as at-risk through automated processes

Apply Cluster Analysis:
a) Apply this most popular data mining method for the discovery of patterns in learning data
i) Interpret the cluster analysis results
b) Use these clusters in learning analytics to solve problems such as:
i) improving participant (student) learning experiences and learning outcomes
ii) increasing retention
iii) providing personalized feedback and support to students

Apply Social Network Analysis (SNA):
Design and Use social networks in Learning Analytics
a) Evidence produced in educational research using SNA including
i) differentiation between self-reported and digitally collected network data;
ii) ethical considerations;
iii) interpretation of basic metrics
b) Analysis of socio-technical networks for
i) Community detection
ii) bipartite network analysis
iii) network clustering
iv) integration with text analysis

Provide personalized learner support:
a) Use data to guide the design and improvements of a learning experience
b) Translate data into actionable knowledge. Data on learning experiences is captured, studied and analysed to inform learner (student) support actions
i) Predict learner (student) behaviour
ii) Deploy personalized support actions for the learners (students)

Application of NLP, NLU (for education research):
a) Identify research problems and questions that can be addressed with natural language data and tools
b) Use unstructured data in educational settings
i) Learner (Student) writing
ii) Responses to learner surveys
iii) Interview data
iv) Transcripts from an educational setting

Multimodal Learning Analytics:
Note: Multimodal learning analytics enable you to understand and optimize learning in real-world environments that do not necessarily use computers during the learning process.
1) Identify if it is appropriate to apply multimodal learning analytics in this research context
2) If feasible, conduct a multimodal learning analytics study
a) Combine and use real-world signals to understand and optimize learning
3) Capture, process, and fuse verbal and nonverbal modes of communication
a) conduct analytics in face-to-face, hands-on, unbounded, and in analog learning settings such as classrooms and labs
b) capture, process, and fuse natural modalities of communication, such as speech, writing, and nonverbal interaction (e.g. movements, gestures, facial expressions, gaze, biometrics, etc.) during real learning activities
c) Use Signal interpretation frameworks (SSI) to work with synchronized data from different modalities


Teaching Analytics – Our Services:

Analytics for educators, classroom trainers / MOOC training providers/affiliated orgs (e.g. CERTaIN, partners, subcontracted trainers etc.)
1) Use teaching analytics to analyse the lesson plans (for class teacher/course designer)
2) Use learning analytics to
a) analyse the classroom delivery of lesson plans
b) learn more about participants’ (students’) learning
3) Reflect on a teacher’s teaching practice by combining insights from both teaching and learning analytics