LEADS Best practices

Incorporating automated tools and analysis in master programme design


Programme design


Private training providers, Public HEI and VET providers


Simona Ramanauskaite, Full professor and senior researcher, Vilnius Gediminas Technical University

  • Master’s degrees and short-term courses in areas including AI, cybersecurity and IoT develeoped and implemented across Estonia, Lithuania, Latvia, Italy and Spain.
  • The programmes are delivered by 4 technical universities, and developed in collaboration with an NGO, two non-profits, a research organisation, a company and SME.
  • Develop automated tools for systematic analysis and monitoring. Solutions implemented:
    • Data scraping from different sources.
    • Usage of data analysis summarising tools to aggregate data.
    • AI and NLP tools to identify similarities and cluster data among programmes.
    • Competency-oriented tool for competency monitoring and further development predictions.
  • Learning environment log data integration with competency tool to get more insight on potential study experience problems and its reasons.
  • Finding the balance between making the programme specific and flexible enough.
  • Addressing both national market needs and student preferences.
  • Ensuring the sustainability of the programme after the project end.
Key takeaways
  • Scheduling Collaborative Online International Learning (COIL) possibilities, maintaining the programme’s structure consistency and bringing in required international experience.
  • Selecting and implementing distance communication technologies (in-person vs. online delivery) which will affect the teaching mode.