SearcharxivSearch

arXiv subjects

Omar Elgohary

Publications and source records attributed to Omar Elgohary.

2 recordsLinked to original sources

Attention, Action, and Memory: How Multi-modal Interfaces and Cognitive Load Alter Information Retention

Each year, multi-modal interaction continues to grow within both industry and academia. However, researchers have yet to fully explore the impact of multi-modal systems on learning and memory retention. This research investigates how combining gaze-based controls with gesture navigation affects information retention when compared to standard track-pad usage. A total of twelve participants read four textual articles through two different user interfaces which included a track-pad and a multi-modal interface that tracked eye movements and hand gestures for scrolling, zooming, and revealing content. Participants underwent two assessment sessions that measured their information retention immediately and after a twenty-four hour period along with the NASA-TLX workload evaluation and the System Usability Scale assessment. The initial analysis indicates that multi-modal interaction produces similar targeted information retention to traditional track-pad usage, but this neutral effect comes with higher cognitive workload demands and seems to deteriorate with long-term retention. The research results provide new knowledge about how multi-modal systems affect cognitive engagement while providing design recommendations for future educational and assistive technologies that require effective memory performance.

cs.HC

Addressing Cold Start For next-article Recommendation

This replication study modifies ALMM, the Adaptive Linear Mapping Model constructed for the next song recommendation, to the news recommendation problem on the MIND dataset. The original version of ALMM computes latent representations for users, last-time items, and current items in a tensor factorization structure and learns a linear mapping from content features to latent item vectors. Our replication aims to improve recommendation performance in cold-start scenarios by restructuring this model to sequential news click behavior, viewing consecutively read articles as (last news, next news) tuples. Instead of the original audio features, we apply BERT and a TF-IDF (Term Frequency-Inverse Document Frequency) to news titles and abstracts to extract token contextualized representations and align them with triplet-based user reading patterns. We also propose a reproducibly thorough pre-processing pipeline combining news filtering and feature integrity validation. Our implementation of ALMM with TF-IDF shows relatively improved recommendation accuracy and robustness over Forbes and Oord baseline models in the cold-start scenario. We demonstrate that ALMM in a minimally modified state is not suitable for next news recommendation.

cs.IR