Filters








72,462 Hits in 3.4 sec

Second workshop on information heterogeneity and fusion in recommender systems (HetRec2011)

Ivan Cantador, Peter Brusilovsky, Tsvi Kuflik
2011 Proceedings of the fifth ACM conference on Recommender systems - RecSys '11  
Information heterogeneity can indeed be identified in any of the pillars of a recommender system: the modeling of user preferences, the description of resource contents, the modeling and exploitation of  ...  feature spaces; d) and ranked recommendation lists could be diverse according to particular user preferences and resource attributes, oriented to groups of users, and driven by multiple user evaluation  ...  Information heterogeneity can indeed be identified in any of the pillars of a recommender system: the modeling of user preferences, the description of resource contents, the modeling and exploitation of  ... 
doi:10.1145/2043932.2044016 dblp:conf/recsys/CantadorBK11 fatcat:b5qc7nhikncvlbn7iovbspnn4y

Tutorial on cross-domain recommender systems

Iván Cantador, Paolo Cremonesi
2014 Proceedings of the 8th ACM Conference on Recommender systems - RecSys '14  
Cross-domain recommender systems aim to generate or enhance personalized recommendations in a target domain by exploiting knowledge (mainly user preferences) form other source domains.  ...  In this tutorial, we formalize the cross-domain recommendation problem, categorize and survey state of the art cross-domain recommender systems, discuss related evaluation issues, and outline future research  ...  The diversity of recommendations can be improved by considering multiple domains, as this may provide a better coverage of the range of user preferences. Enhancing user models.  ... 
doi:10.1145/2645710.2645777 dblp:conf/recsys/CantadorC14 fatcat:uut6h7xanzal7h4mgz65w3ocqi

Mining Semantic Data, User Generated Contents, and Contextual Information for Cross-Domain Recommendation [chapter]

Ignacio Fernández-Tobías
2013 Lecture Notes in Computer Science  
Cross-domain recommender systems suggest items in a target domain by exploiting user preferences and/or domain knowledge available in a source domain.  ...  For this purpose, we investigate a number of approaches to extract, process, and integrate knowledge for linking distinct domains, and various models that exploit such knowledge for making effective recommendations  ...  E-commerce sites like Amazon, however, could take benefit from exploiting the user's preferences on diverse types of items to provide recommendations in different but somehow related domains.  ... 
doi:10.1007/978-3-642-38844-6_42 fatcat:qldfechwmrh5zctkaeq5n2jrjq

Proposed Collaborative Filtering Recommender System Based on Implicit and Explicit User's Preferences

2018 Iraqi Journal of Science  
This research proposed a recommender system that uses user's reviews as implicit feedback to extract user preferences from their reviews to enhance personalization in addition to the explicit ratings.  ...  The expansion of web applications like e-commerce and other services yields an exponential increase in offers and choices in the web.  ...  The idea of this module is simple; it aims to fulfill the diversity by equalization the recommendation result list between user preferences and k-furthest neighbors users preferences.  ... 
doi:10.24996/ijs.2018.59.2a.15 fatcat:4kdbkq7kdnenxedbapi7ipx5wm

User Diverse Preference Modeling by Multimodal Attentive Metric Learning

Fan Liu, Zhiyong Cheng, Changchang Sun, Yinglong Wang, Liqiang Nie, Mohan Kankanhalli
2019 Proceedings of the 27th ACM International Conference on Multimedia - MM '19  
In particular, for each user-item pair, we propose an attention neural network, which exploits the item's multimodal features to estimate the user's special attention to different aspects of this item.  ...  Extensive experiments on large-scale real-world datasets show that our model can substantially outperform the state-of-the-art baselines, demonstrating the potential of modeling user diverse preference  ...  The results show that our method significantly outperforms a variety of competitors, demonstrating the effectiveness of our method and the potential of modeling user diverse preference for recommendation  ... 
doi:10.1145/3343031.3350953 dblp:conf/mm/LiuCSWNK19 fatcat:3n72o3u7yzcbjobmpui4ts2vfe

Spoiled for Choice? Personalized Recommendation for Healthcare Decisions: A Multi-Armed Bandit Approach [article]

Tongxin Zhou, Yingfei Wang, Lu Yan, Yong Tan
2020 arXiv   pre-print
variations while promoting recommendation diversity in the meantime.  ...  Taking into account that users' health behaviors can be highly dynamic and diverse, we propose a multi-armed bandit (MAB)-driven recommendation framework, which enables us to adaptively learn users' preference  ...  Figure 6 Performance Variation for Dynamic Users 5.5 Experiment 5: Diversity Analysis effectively learn users' diverse challenge preferences in the data.  ... 
arXiv:2009.06108v1 fatcat:rs7utaw2sfa45dajb6mnzm4qcu

Listener-Aware Music Recommendation from Sensor and Social Media Data [chapter]

Markus Schedl
2015 Lecture Notes in Computer Science  
In this note, we summarize our recent work and report our latest findings on the topics of tailoring music recommendations to individual listeners and to groups of listeners sharing certain characteristics  ...  We focus on two tasks: context-aware automatic playlist generation (also known as serial recommendation) using sensor data and music artist recommendation using social media data.  ...  The author would further like to thank his colleagues and students who contributed to the work at hand.  ... 
doi:10.1007/978-3-319-23461-8_16 fatcat:h4sjiiv52jfdtl3jdwkxt6tty4

News Recommender Based on Rich Feedback [chapter]

Liliana Ardissono, Giovanna Petrone, Francesco Vigliaturo
2015 Lecture Notes in Computer Science  
The experimental results we carried out provided encouraging results about the accuracy of the recommendations.  ...  Moreover it presents a hybrid news recommender which suggest news items on the basis of the reader's short and long-term reading history, taking reading trends and short-term interests into account.  ...  -The short-term content-based recommender predicts U 's preference for i by exploiting her/his recent interests in news stories whose content is similar to that of i.  ... 
doi:10.1007/978-3-319-20267-9_27 fatcat:6t4ct5piorhs7myg5nrhecpohy

A framework for diversifying recommendation lists by user interest expansion

Zhu Zhang, Xiaolong Zheng, Daniel Dajun Zeng
2016 Knowledge-Based Systems  
The framework enhances the diversity of users' preferences by expanding the sizes and categories of the original user-item interaction records, and then adopts traditional recommendation models to generate  ...  Recommender systems have been widely used to discover users' preferences and recommend interesting items to users during this age of information load.  ...  Acknowledgments We would like to thank each member of the SMILES group in the Institute of Automation, Chinese Academy of Sciences.  ... 
doi:10.1016/j.knosys.2016.05.010 pmid:28959089 pmcid:PMC5613956 fatcat:qok3bad52bcabhhrfgccvhxowy

Exploiting various implicit feedback for collaborative filtering

Byoungju Yang, Sangkeun Lee, Sungchan Park, Sang-goo Lee
2012 Proceedings of the 21st international conference companion on World Wide Web - WWW '12 Companion  
In this paper, we show that users' diverse implicit feedbacks can be significantly used to improve recommendation accuracy.  ...  Existing researches generally use a pseudo-rating matrix by adding up the number of item consumption; however, this naïve approach may not capture user preferences correctly in that many other important  ...  The experimental result shows that assigning different weights to diverse user activities for creating a pseudomatrix could largely affect the recommendation accuracy, and the best cases outperformed the  ... 
doi:10.1145/2187980.2188166 dblp:conf/www/YangLPL12 fatcat:lvcuovjyybhsbe6t5fc5db55rq

The Semantics of Movie Metadata: Enhancing User Profiling for Hybrid Recommendation [chapter]

Márcio Soares, Paula Viana
2017 Advances in Intelligent Systems and Computing  
The influence of each of the standard description elements (actors, directors and genre) in representing user's preferences is analyzed.  ...  In movie/TV collaborative recommendation approaches, ratings users gave to already visited content are often used as the only input to build profiles.  ...  Acknowledgment The work was partially supported by FourEyes, a RL within Project "TEC4Growth -Pervasive Intelligence, Enhancers and Proofs of Concept with Industrial Impact/NORTE-01-0145-FEDER-000020",  ... 
doi:10.1007/978-3-319-56535-4_33 fatcat:eq5pr6eclnc73a244qsu7abx2a

An Intelligent Recommendation Service for Student-Selection on Research Social Network: Bridging the Gap Between Students and Supervisors—Research-in-Progress

Ming-Yu ZHANG, Jian-Shan SUN
2019 DEStech Transactions on Social Science Education and Human Science  
Then, it applies respective recommendation strategy to provide student recommendation services for the target supervisor.  ...  On account of the information asymmetry, it poses a significant challenge for supervisors to find the most appropriate students. Current studies are limited to the context of one university.  ...  Acknowledgements This paper is sponsored by the project from Fujian Provincial Education Department (No.JAS180414) and a School-level Research Project of Putian University (No.2018061).  ... 
doi:10.12783/dtssehs/icesd2019/28161 fatcat:dbmi6pwn6vbqpf43p3fufh6zku

The Era of Intelligent Recommendation: Editorial on Intelligent Recommendation with Advanced AI and Learning

Shoujin Wang, Gabriella Pasi, Liang Hu, Longbing Cao
2020 IEEE Intelligent Systems  
Second, we express our sincere gratitude to the IS team led by Professor Venkatramanan Subrahmanian for their support and help to ensure the timely publication of this issue.  ...  After a long period of hard-work of review from anonymous reviewers and careful revisions from the authors, we finally achieve the current versions of the accepted papers published in this issue.  ...  In addition, PGIM is able to make diversity-promoting recommendations by extracting user diversity preferences from interactions among users.  ... 
doi:10.1109/mis.2020.3026430 fatcat:4myxztm6bzexlc6z7fffddnnk4

Semrevrec: A Recommender System Based On User Reviews And Linked Data [article]

Iacopo Vagliano, Diego Monti, Maurizio Morisio
2018 Zenodo  
Traditionally, recommender systems exploit user ratings to infer preferences. However, the growing popularity of social platforms has encouraged users to write textual reviews about liked items.  ...  In this paper we propose a novel recommendation approach based on the semantic annotation of entities mentioned in user reviews and on the knowledge available in the Web of Data.  ...  ACKNOWLEDGMENTS This work was supported by the EU's Horizon 2020 programme under grant agreement H2020-693092 MOVING.  ... 
doi:10.5281/zenodo.1157831 fatcat:aytuttz6rnayfcv5q3xfs32oau

Evolution of the user's content: An Overview of the state of the art [article]

Djallel Bouneffouf
2013 arXiv   pre-print
The evolution of the user's content still remains a problem for an accurate recommendation.This is why the current research aims to design Recommender Systems (RS) able to continually adapt information  ...  that matches the user's interests.  ...  Table 1 : 1 Approaches for following the user's content evolution Recommendations similar to the user's history The lack of diversity in recommendations.Exploration / Exploitation Trade-off Li et al.[2010b  ... 
arXiv:1305.1787v1 fatcat:374ry747fjckdkiylvozg7tlti
« Previous Showing results 1 — 15 out of 72,462 results