A new user study on music recommendation systems reveals that while users can perceive differences in the popularity composition of recommended track lists, they do not consistently prefer calibrated lists. The research also found that the effectiveness of popularity calibration metrics, such as Jensen-Shannon divergence (JSD), is inconsistent and depends on factors like item familiarity and the availability of user history. Furthermore, computational popularity labels showed only a weak alignment with users' own judgments of popularity, suggesting a need for a more critical understanding of calibration as both a metric and a user-facing feature. AI
IMPACT Findings suggest current popularity calibration methods in recommender systems may not align with user preferences, potentially impacting the design of future personalization algorithms.
RANK_REASON Research paper published on arXiv detailing a user study about recommender systems. [lever_c_demoted from research: ic=1 ai=0.7]
Read on arXiv cs.IR (Information Retrieval) →
- alphaXiv
- arXiv
- CatalyzeX Code Finder for Papers
- Connected Papers
- DagsHub
- Doctor of Juridical Science
- Gotit.pub
- Hugging Face
- information retrieval
- Litmaps
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
