Zobrazeno 1 - 10
of 67 079
pro vyhledávání: '"User profiles"'
Autor:
Hidri, Minyar Sassi
Publikováno v:
Interdisciplinary Journal of Information, Knowledge, and Management, Volume 19, 2024, pp. 010
This study contributes to the literature by considering the difference in vocabulary used to express document content and information needs. Users are integrated into all research phases in order to provide them with relevant information adapted to t
Externí odkaz:
http://arxiv.org/abs/2405.15791
Most conventional recommendation methods (e.g., matrix factorization) represent user profiles as high-dimensional vectors. Unfortunately, these vectors lack interpretability and steerability, and often perform poorly in cold-start settings. To addres
Externí odkaz:
http://arxiv.org/abs/2402.15623
Recent state-of-the-art recommender systems predominantly rely on either implicit or explicit feedback from users to suggest new items. While effective in recommending novel options, many recommender systems often use uninterpretable embeddings to re
Externí odkaz:
http://arxiv.org/abs/2402.05810
This paper explores a novel technique for improving recall in cross-language information retrieval (CLIR) systems using iterative query refinement grounded in the user's lexical-semantic space. The proposed methodology combines multi-level translatio
Externí odkaz:
http://arxiv.org/abs/2402.13500
In the information age we are living in today, not only are we interested in accessing multimedia objects such as documents, videos, etc. but also in searching for professional experts, people or celebrities, possibly for professional needs or just f
Externí odkaz:
http://arxiv.org/abs/2401.10634
Recommender systems are most successful for popular items and users with ample interactions (likes, ratings etc.). This work addresses the difficult and underexplored case of supporting users who have very sparse interactions but post informative rev
Externí odkaz:
http://arxiv.org/abs/2311.01314
Autor:
Barkan, Oren1 (AUTHOR), Shaked, Tom2 (AUTHOR), Fuchs, Yonatan2 (AUTHOR), Koenigstein, Noam3 (AUTHOR) noamk@tauex.tau.ac.il
Publikováno v:
User Modeling & User-Adapted Interaction. Apr2024, Vol. 34 Issue 2, p375-405. 31p.
Autor:
Knöchelmann, Anja1 (AUTHOR) anja.knoechelmann@medizin.uni-halle.de, Healy, Karl1 (AUTHOR), Frese, Thomas2 (AUTHOR), Kantelhardt, Eva3 (AUTHOR), Mikolajczyk, Rafael4 (AUTHOR), Meyer, Gabriele5 (AUTHOR), Schildmann, Jan6 (AUTHOR), Steckelberg, Anke5 (AUTHOR), Herke, Max1 (AUTHOR)
Publikováno v:
BMC Health Services Research. 9/17/2024, Vol. 24 Issue 1, p1-10. 10p.
Autor:
Rousseau, Elzette1 (AUTHOR) Elzette.Rousseau@hiv-research.org.za, Sikkema, Kathleen J.2 (AUTHOR), Julies, Robin F.3 (AUTHOR), Mazer, Katelyn4 (AUTHOR), O'Malley, Gabrielle5 (AUTHOR), Heffron, Renee6 (AUTHOR), Morton, Jennifer F.5 (AUTHOR), Johnson, Rachel5 (AUTHOR), Celum, Connie5 (AUTHOR), Baeten, Jared M.5 (AUTHOR), Bekker, Linda‐Gail1 (AUTHOR)
Publikováno v:
Journal of the International AIDS Society. May2024, Vol. 27 Issue 5, p1-9. 9p.
Methods for making high-quality recommendations often rely on learning latent representations from interaction data. These methods, while performant, do not provide ready mechanisms for users to control the recommendation they receive. Our work tackl
Externí odkaz:
http://arxiv.org/abs/2304.04250