Filters








32,168 Hits in 8.0 sec

Repeat Consumption Recommendation Based on Users Preference Dynamics and Side Information

Dimitrios Rafailidis, Alexandros Nanopoulos
2015 Proceedings of the 24th International Conference on World Wide Web - WWW '15 Companion  
Repeat consumption recommendations are generated based on factorizing the coupled tensor, by weighting the importance of past user preferences according to the captured rate.  ...  We present a Coupled Tensor Factorization model to recommend items with repeat consumption over time.  ...  consequently the model cannot identify any other user to base the recommendation according to the side information of the d-th attribute.  ... 
doi:10.1145/2740908.2742732 dblp:conf/www/RafailidisN15a fatcat:rbtxbjlezfgjzgx6ayss7q5qki

Intelligent interaction based on holographic personalized portal

Yadong Huang, Yueting Chai, Yi Liu, Xiang Gu
2017 International Journal of Crowd Science  
The holographic personality portal is based on holographic enterprises, commodities and consumers, and the personalized portal consists of accurate ontology, reliable supply, intelligent demand and smart  ...  Design/methodology/approach -In this paper, the authors propose crowd-science industrial ecological system based on holographic personalized portal and its interaction.  ...  The personalized demand information, based on the user preference, basic information and instant demand information, is recognized by the demand-recognition system.  ... 
doi:10.1108/ijcs-08-2017-0016 fatcat:thdq5xvzfnaydflgpivqm5gvju

Understanding Longitudinal Dynamics of Recommender Systems with Agent-Based Modeling and Simulation [article]

Gediminas Adomavicius and Dietmar Jannach and Stephan Leitner and Jingjing Zhang
2021 arXiv   pre-print
Today's research in recommender systems is largely based on experimental designs that are static in a sense that they do not consider potential longitudinal effects of providing recommendations to users  ...  In this paper, we discuss how Agent-Based Modeling and Simulation (ABM) techniques can be used to study such important longitudinal dynamics of recommender systems.  ...  INTRODUCTION AND MOTIVATION Recommender systems can exert significant influence on how users navigate information spaces and make decisions.  ... 
arXiv:2108.11068v1 fatcat:pbi6oxnwp5amhnhxsi6omrs6ny

A Novel Method Providing Multimedia Contents According to Preference Clones in Mobile Environment [chapter]

Sanggil Kang, Sungjoon Park
2007 Lecture Notes in Computer Science  
We also implemented our system based on Java Micro Edition platform.  ...  From the binary decision tree, we identify the preference clones of each target user by matching the target user's consumption behavior to that of each sub-group in the BDT with a sequential manner.  ...  Then, it recommends preferred contents to each target user. The client side has one module called Information Manager Module (IMM). The IMM displays recommendation list provided from the server side.  ... 
doi:10.1007/978-3-540-72588-6_134 fatcat:pujib3le2zfa5bsjjjqkvihfu4

Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations [article]

Hui Fang, Danning Zhang, Yiheng Shu, Guibing Guo
2020 arXiv   pre-print
In the field of sequential recommendation, deep learning (DL)-based methods have received a lot of attention in the past few years and surpassed traditional models such as Markov chain-based and factorization-based  ...  In this view, this survey focuses on DL-based sequential recommender systems by taking the aforementioned issues into consideration.  ...  [2] investigated the dynamics of repeated consumption on seven real datasets and found that recency is the strongest predictor of repeated consumption. Bhagat et al.  ... 
arXiv:1905.01997v3 fatcat:i7hvdiqjpnaupcq2osrblttb4u

The emergence of Explainability of Intelligent Systems: Delivering Explainable and Personalised Recommendations for Energy Efficiency [article]

Christos Sardianos and Iraklis Varlamis and Christos Chronis and George Dimitrakopoulos and Abdullah Alsalemi and Yassine Himeur and Faycal Bensaali and Abbes Amira
2020 arXiv   pre-print
In this work, we focus on a context-aware recommendation system for energy efficiency and develop a mechanism for explainable and persuasive recommendations, which are personalized to user preferences  ...  Based on a study conducted using a Telegram bot, different scenarios have been validated with actual data and human feedback.  ...  Consumption habits: Based on the consumption data analysis, the system identifies the energy consumption preferences of the user in terms of when the user tends to turn-on and off certain devices and combining  ... 
arXiv:2010.04990v1 fatcat:z4caknr7mnbx5b5wuay5psfrhq

Learning from History and Present

Zhi Li, Hongke Zhao, Qi Liu, Zhenya Huang, Tao Mei, Enhong Chen
2018 Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18  
In the modern e-commerce, the behaviors of customers contain rich information, e.g., consumption habits, the dynamics of preferences.  ...  In this paper, we propose a novel Behavior-Intensive Neural Network (BINN) for next-item recommendation by incorporating both users' historical stable preferences and present consumption motivations.  ...  The dynamics and evolutions of users' preferences, and also their present consumption motivations are usually not given special attentions.  ... 
doi:10.1145/3219819.3220014 dblp:conf/kdd/LiZLHMC18 fatcat:klof7eqrc5hajdyin2m3mab3he

Do Search Algorithms Endanger Democracy? An Experimental Investigation of Algorithm Effects on Political Polarization

Jaeho Cho, Saifuddin Ahmed, Martin Hilbert, Billy Liu, Jonathan Luu
2020 Journal of Broadcasting & Electronic Media  
recommender system based on either "self" preference or "social" preference.  ...  Indeed, information recommender systems based on big data and algorithms are a key gateway through which most users navigate, select, and consume information online (Beam, 2014; Ricci et al., 2011) .  ...  to train the search/ recommender algorithm.  ... 
doi:10.1080/08838151.2020.1757365 fatcat:lloz7trbf5devio6lcup3vsnlm

Embedding Factorization Models for Jointly Recommending Items and User Generated Lists

Da Cao, Liqiang Nie, Xiangnan He, Xiaochi Wei, Shunzhi Zhu, Tat-Seng Chua
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
On one hand, user generated lists contain rich signal about item co-occurrence, as items within a list are usually gathered based on a speci c theme.  ...  Speci cally, we employ factorization model to capture users' preferences over items and lists, and utilize embeddingbased models to discover the co-occurrence information among items and lists. e gap between  ...  It weights items within lists based on both position of items and personalized list consumption pa ern.  ... 
doi:10.1145/3077136.3080779 dblp:conf/sigir/CaoN0WZC17 fatcat:kpfuipswajhyxbykoac7jhgvgq

Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback [article]

Jiawei Chen, Can Wang, Sheng Zhou, Qihao Shi, Jingbang Chen, Yan Feng, Chun Chen
2020 arXiv   pre-print
To achieve both adaptive weights assignment and efficient model learning, we propose a fast adaptively weighted matrix factorization (FAWMF) based on variational auto-encoder.  ...  Further, to support fast and stable learning of FAWMF, a new specific batch-based learning algorithm fBGD has been developed, which trains on all feedback data but its complexity is linear to the number  ...  Here we do not compare with existing dynamic sampling strategies, since they either suffer from efficiency problems or require other side information.  ... 
arXiv:2003.01892v1 fatcat:iensz3pbzjbtfgk3b5kp3qz5p4

A Novel Recommendation Algorithm Incorporating Temporal Dynamics, Reviews and Item Correlation

Ting WU, Yong FENG, JiaXing SANG, BaoHua QIANG, YaNan WANG
2018 IEICE transactions on information and systems  
Recommender systems (RS) exploit user ratings on items and side information to make personalized recommendations.  ...  Besides, the review text accompanied with a rating score can help us to understand why a user likes or dislikes an item, so temporal dynamics and text information in reviews are important side information  ...  Conclusion and Future Work In the study of recommender systems, besides the explicit ratings, side information like temporal dynamics, reviews information and item correlation provide both opportunities  ... 
doi:10.1587/transinf.2017edp7387 fatcat:eyefclz6qre2xfvycsjuqrftsu

Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback

Jiawei Chen, Can Wang, Sheng Zhou, Qihao Shi, Jingbang Chen, Yan Feng, Chun Chen
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
(FAWMF) based on variational auto-encoder.  ...  Further, to support fast and stable learning of FAWMF, a new specific batch-based learning algorithm fBGD has been developed, which trains on all feedback data but its complexity is linear to the number  ...  ACKNOWLEDGMENTS This work is supported by National Natural Science Foundation of China (Grant No: U1866602) and National Key Research and Development Project (Grant No: 2018AAA0 101503).  ... 
doi:10.1609/aaai.v34i04.5751 fatcat:jzwi7d2en5affoglyhfxbm7noa

On-site Trip Planning Support System Based on Dynamic Information on Tourism Spots

Masato Hidaka, Yuki Kanaya, Shogo Kawanaka, Yuki Matsuda, Yugo Nakamura, Hirohiko Suwa, Manato Fujimoto, Yutaka Arakawa, Keiichi Yasumoto
2020 Smart Cities  
The proposed system consists of the following two key mechanisms: (A) A mechanism for acquiring preference information from tourists (including preference on dynamic information); (B) a curation mechanism  ...  However, in many existing systems, serious problems occur, such as (1) a lack of support for on-site use, (2) a lack of consideration of dynamic information, and (3) heavy burden on tourists.  ...  The on-site tourism curation mechanism recommends four candidate tourism spots to go to next based on the acquired preferences of a participant, the participant's current location, and dynamic information  ... 
doi:10.3390/smartcities3020013 fatcat:yrffiixu6jaw3bkjdbp3zhq3ly

Revealing the Unobserved by Linking Collaborative Behavior and Side Knowledge [article]

Evgeny Frolov, Ivan Oseledets
2018 arXiv   pre-print
We propose a tensor-based model that fuses a more granular representation of user preferences with the ability to take additional side information into account.  ...  The general formulation of the approach imposes no restrictions on the type of observed interactions and makes it potentially applicable for joint modelling of context information along with side data.  ...  Based on the remark about the curse of dimensionality problem of TD, another interesting direction for research is applying the key ideas presented in this work to more appropriate tensor formats such  ... 
arXiv:1807.10634v1 fatcat:uzit3f5w2jdzhhl674xm4gotnu

Do Social Explanations Work? Studying and Modeling the Effects of Social Explanations in Recommender Systems [article]

Amit Sharma, Dan Cosley
2013 arXiv   pre-print
Based on these insights, we present a generative probabilistic model that explains the interplay between explanations and background information on music preferences, and how that leads to a final likelihood  ...  We start with an experiment with 237 users, in which we show explanations with varying levels of social information and analyze their effect on users' decisions.  ...  In the second phase, the user evaluates the item itself, based on her consumption experience.  ... 
arXiv:1304.3405v1 fatcat:b7jexr4ddzcvvfnxlsee56vywa
« Previous Showing results 1 — 15 out of 32,168 results