Researchers have developed "Ranking Companion," a novel visual analytics system designed to improve the creation of personalized item rankings. This approach addresses the challenge of users lacking domain knowledge or the ability to articulate specific preferences by allowing them to express preferences through judgments on known items. Ranking Companion integrates six different item-selection methods, combining model-driven active learning with human-driven selection to offer users greater flexibility and control. A user study with 10 participants indicated trade-offs in perceived ranking quality across accuracy, diversity, novelty, transparency, control, and satisfaction when using these hybrid methods. AI
IMPACT This research offers a new framework for personalized item ranking, potentially improving user experience in recommendation systems and information retrieval tools.
RANK_REASON The item is a research paper detailing a new approach and system for item-based ranking. [lever_c_demoted from research: ic=1 ai=0.7]
Read on arXiv cs.IR (Information Retrieval) →
- arXiv
- CatalyzeX Code Finder for Papers
- Connected Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- human–computer interaction
- Influence Flower
- information retrieval
- Litmaps
- Ranking Companion
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
