Background:
The COVID-19 pandemic has significantly accelerated the shift toward online and blended learning in higher education, placing renewed emphasis on the individualization of learning content to meet diverse student needs. Even high-quality learning materials may fail to engage learners if they do not align with students’ personal preferences and learning styles. Identifying these learner preferences, therefore, emerges as a critical challenge.

Objectives:
This paper presents ongoing work within a larger research project aimed at employing artificial intelligence to recommend optimal learning path for students in specific courses. Beyond mere optimization, the goal is to ensure the best possible fit between learning materials and individual learners.

Sample & Methods:
A total of 27 students from technical degree programs took part in this survey. All participation was voluntary, and data were handled in full compliance with GDPR regulations. Although our broader project integrates fine-grained learning analytics from Moodle, the present abstract focuses exclusively on the self-report questionnaire results. Participants completed five instruments:
1. Index of Learning Styles (ILS)
2. LIST-K (Learning and Study Strategies Inventory – Short version)
3. BFI-10 (Big Five Inventory – 10 items)
4. Custom Preferences Instrument, capturing preferences for specific learning elements (e.g. instructional videos, lecture notes, summaries) and basic demographic data
5. Motivational Value Systems Questionnaire (MVSQ), piloted last semester to assess value orientations and motivational drivers

Results:
Preliminary analyses of the questionnaire data reveal:
- Learning Styles (ILS): The majority lean toward the visual learning type (M = 5.740, SD = 3.430).
- Learning Strategies (LIST-K): High scores on metacognitive strategies (M = 3.000; SD = 0.520) and collaboration with peers (M = 3.190; SD = 0.540).
- Preferred Learning Elements: Summaries, overviews, and self-checks are most favored.
- Value Orientations (MVSQ): Students are primarily driven by the pursuit of personal achievement (M = 4.400; SD = 11.140).

Conclusion & Significance:
By integrating these five standardized questionnaires, we gain valuable insights into student learning preferences—insights that complement our Moodle analytics in the broader project. Observed trends suggest that learning materials should be concise and designed to facilitate peer interaction and knowledge deepening. These findings will guide the refinement of our AI-driven recommendation engine, enhancing its ability to deliver personalized learning paths that boost both engagement and effectiveness.

Keywords: AI in higher education, learning management system, adaptive learning, personalized learning paths, online and blended learning.