V ponedeljek, 30. marca 2026, bo ob 16:00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 30. marec 2026 ob 16.00 v FAMNIT-VP3.

------------------------------------------------------------------------------------
PREDAVATELJICI: Karolina TRAJKOVSKA in Michelle FERNANDO
------------------------------------------------------------------------------------

Karolina Trajkovska is a PhD student and researcher at UP FAMNIT. She is a young researcher in HCI/UX, contributing to research on how people interact with digital systems, especially using modern techniques like eye-tracking and augmented reality.

Michelle Fernando is a PhD student and teaching assistant at UP FAMNIT, where she works with the HICUP Lab. She received the B.Sc. (Hons) degree in computer science from the University of Colombo, Sri Lanka. Her research focuses on human-computer interaction, extended reality, and human motion analysis in the context of sports training and skill acquisition.

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Beyond Rote Memorisation: The Impact of AI-Generated Visuals and Personalised Mnemonics on Vocabulary Retention
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Mnemonics, such as the keyword method, are effective for vocabulary learning, where learners form a mental image cues linking a foreign word to a phonetically similar word in a familiar language. However, many avoid mnemonics because generating these cues is cognitively demanding. The first aim of this study is to examine whether non-personalised (pre-generated) cues can decrease cognitive effort while maintaining performance compared with personalised (self-generated) cues. The second aim is to compare externalised cues in image and video formats, using novel text-to-images/video generation. We built an interactive tool and ran a mixed-design study with 32 participants, manipulating PERSONALISATION (personalised vs non-personalised mnemonic cues) and MODALITY (images vs videos). The analysis is presented in two parts:
Part I (presented by Karolina Trajkovska):
Performance & Efficiency.  Personalised cues produced significantly better immediate and delayed recall but took more time and increased perceived workload, whereas non-personalised cues were more efficient in recall per unit time. Despite this, participants preferred personalised cues, suggesting subjective benefits beyond performance. Finally, modality showed no significant differences, though images had a modest advantage.
Part II (presented by Michelle Fernando):
Biometric data collection & Emotional Engagement. We detail the collection and analysis of biometric data to evaluate physiological correlates of the "personalisation effect." This explores how self-generation influences emotional arousal and cognitive investment compared to passive consumption of cues. The statistical analysis shows a significant main effect of PERSONALISATION on emotional engagement.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP3 s pričetkom ob 16:00 uri.

Vabljeni!