620,457 Hits in 6.1 sec

On component interactions in two-stage recommender systems [article]

Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus
2022 arXiv   pre-print
Such treatment presupposes that the two-stage performance is explained by the behavior of the individual components in isolation.  ...  Despite their popularity, the literature on two-stage recommenders is relatively scarce, and the algorithms are often treated as mere sums of their parts.  ...  Acknowledgments and Disclosure of Funding The authors thank Matej Balog, Mateo Rojas-Carulla, and Richard Turner for their useful feedback on early versions of this manuscript.  ... 
arXiv:2106.14979v3 fatcat:xhwu5vwkzbdnljyndvx6vvtasm

A two-stage framework for designing visual analytics system in organizational environments

Xiaoyu Wang, Wenwen Dou, Thomas Butkiewicz, Eric A. Bier, William Ribarsky
2011 2011 IEEE Conference on Visual Analytics Science and Technology (VAST)  
To alleviate these problems, we present a two-stage framework for informing the design of a visual analytics system.  ...  We illustrate both stages and their design components through examples, and hope this framework will be useful for designing future visual analytics systems.  ...  In the subsequent sections, we present the details of our two-stage design framework and its related design components. We organize these components into two design stages.  ... 
doi:10.1109/vast.2011.6102463 dblp:conf/ieeevast/WangDBBR11 fatcat:xxdxam3ysravzmsfijdfikfwwq

Quantifying and Mitigating Popularity Bias in Conversational Recommender Systems [article]

Shuo Lin, Jianling Wang, Ziwei Zhu, James Caverlee
2022 arXiv   pre-print
Conversational recommender systems (CRS) have shown great success in accurately capturing a user's current and detailed preference through the multi-round interaction cycle while effectively guiding users  ...  Perhaps surprisingly, conversational recommender systems can be plagued by popularity bias, much like traditional recommender systems.  ...  Inspired by [32] , research in [20] further strengthens the interaction between the recommender component and the conversation component by proposing a three-stage framework that inherently adapts to  ... 
arXiv:2208.03298v1 fatcat:5qxzsqlz4fh3ppkjfj7iqxckrm

Designing Explanation Interfaces for Transparency and Beyond

Chun-Hua Tsai, Peter Brusilovsky
2019 International Conference on Intelligent User Interfaces  
We went through four stages to identify the key components of the recommendation model, expert mental model, user mental model, and target mental model.  ...  In this work-in-progress paper, we presented a participatory process of designing explanation interfaces for a social recommender system with multiple explanatory goals.  ...  In the first stage, we discussed the Expert Mental Model by discussing the key components (based on the similarity algorithm) of each recommendation model.  ... 
dblp:conf/iui/TsaiB19a fatcat:357kg7ggcrc67d5dmqyuipwaya

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, Tat-Seng Chua
2020 Proceedings of the 13th International Conference on Web Search and Data Mining  
A successful Conversational Recommender System (CRS) requires proper handling of interactions between conversation and recommendation.  ...  In this work, we fill this missing interaction framework gap by proposing a new CRS framework named Estimation-Action-Reflection, or EAR, which consists of three stages to better converse with users. (  ...  PROPOSED METHODS EAR consists of a recommendation and conversation component (RC and CC) which interact intensively in the three-stage conversational process.  ... 
doi:10.1145/3336191.3371769 dblp:conf/wsdm/Lei0MWHKC20 fatcat:zwq72cr3ifh4jgtidobcvxnf4e

Deep Learning Framework for Online Interactive Service Recommendation in Iterative Mashup Development [article]

Yutao Ma, Xiao Geng, Jian Wang, Keqing He, Dionysis Athanasopoulos
2021 arXiv   pre-print
Experiments on a real-world dataset indicate that HISR outperforms several state-of-the-art service recommendation methods in the online interactive scenario for developing new mashups iteratively.  ...  How to recommend suitable follow-up component services to develop new mashups has become a fundamental problem in service-oriented software engineering.  ...  A service recommendation system (SRS) usually provides suggestions for component services in the development process.  ... 
arXiv:2101.02836v1 fatcat:lgbicp3oerflfixxi76kfyhfne

DIETORECS: Travel Advisory for Multiple Decision Styles [chapter]

Daniel R. Fesenmaier, Francesco Ricci, Schaumlechner Erwin, Wöber Karl, Zanella Cristiano
2003 Information and Communication Technologies in Tourism 2003  
This paper presents Dietorecs, a novel case-based travel planning recommender system.  ...  The dialogue (questions) is personalized using both the user model (cases) and statistics over the data available in the virtual catalogues provided by two DMOs.  ...  Conclusions The proposed Dietorecs system represents a new generation of travel recommender systems that can cope with individual differences in travel wishes and decision styles.  ... 
doi:10.1007/978-3-7091-6027-5_25 dblp:conf/enter/Fesenmaier0SWZ03 fatcat:2snckjfqjzfdbfukxlechq3724

Conversational Recommender Systems Based on Mobile Chatbot for Culinary

Ghazi Ahmad Fadhlullah, Z K Abdurahman Baizal, Nurul Ikhsan
In the previous research on the recommendation system for culinary places, users only gave their preferences at the beginning of the recommendation process and ignored the operating hours of the recommended  ...  We use the Conversational Recommender System on the chatbot platform with the Personalized PageRank algorithm to generate recommendations.  ...  This component has two approaches in detecting entities, namely spotting and disambiguation.  ... 
doi:10.30865/mib.v5i4.3242 fatcat:xiuxj2eimjh3dbscgxyxrdks6i

Embedding-based Recommender System for Job to Candidate Matching on Scale [article]

Jing Zhao, Jingya Wang, Madhav Sigdel, Bopeng Zhang, Phuong Hoang, Mengshu Liu, Mohammed Korayem
2021 arXiv   pre-print
One of the major challenges in an online recruitment scenario is to provide good matches between job posts and candidates using a recommender system on the scale.  ...  Both offline and online evaluation results indicate a significant improvement of our proposed two-staged embedding-based system in terms of click-through rate (CTR), quality and normalized discounted accumulated  ...  CANDIDATE MATCHING SYSTEM AND ARCHITECTURE The proposed architecture of the two-staged recommendation system consists of two major components ( Figure 4 ): (1) First stage retrieval component that utilizes  ... 
arXiv:2107.00221v1 fatcat:rgj2hqndwvaoxbl3nscff4udum

Adaptive Learning Guidance System (ALGS) [article]

Ghada El-Hadad, Doaa Shawky, Ashraf Badawi
2019 arXiv   pre-print
This is where the hybrid recommendation system plays a crucial role in the 3-stage ALGS architecture. The second issue addressed is the need for big data to enhance the system functionality.  ...  Most past studies marginalized the teacher role in adaptive learning system, particularly the online ones.  ...  Stage 2: Hybrid Recommendation System The hybrid recommendation system is hybrid on two levels: collaborative filtering (CF)content-based (CB) hybrid recommender, and machine-teacher hybrid.  ... 
arXiv:1911.06812v1 fatcat:shz6dvof6fgzlb7x26fy3tekdq

Pathway-Finder: An Interactive Recommender System for Supporting Personalized Care Pathways

Rui Liu, Raj Velamur Srinivasan, Kiyana Zolfaghar, Si-Chi Chin, Senjuti Basu Roy, Aftab Hasan, David Hazel
2014 2014 IEEE International Conference on Data Mining Workshop  
In this demonstration paper, we propose Pathway-Finder, an interactive recommender system to visually explore and discover clinical pathways.  ...  Additionally, the system implements a big-data infrastructure using Spark that is hosted as a HDinsight cluster on Microsoft Azure for Research platform to support real-time recommendation and visualization  ...  Based on all the user inputs in from the first three stages, our system predicts the Readmission Risk of the patient.  ... 
doi:10.1109/icdmw.2014.37 dblp:conf/icdm/LiuSZCRHH14 fatcat:nves22rea5adjj5lovrtohjtje

Dionysius: A Framework for Modeling Hierarchical User Interactions in Recommender Systems [article]

Jian Wang, Krishnaram Kenthapadi, Kaushik Rangadurai, David Hardtke
2017 arXiv   pre-print
We implemented and deployed this system as part of the recommendation platform at LinkedIn for more than one year.  ...  We address the following problem: How do we incorporate user item interaction signals as part of the relevance model in a large-scale personalized recommendation system such that, (1) the ability to interpret  ...  Testing Stage In the model testing stage, we used two datasets, for learning user interaction fields and for providing recommendations respectively.  ... 
arXiv:1706.03849v1 fatcat:ww7md2lzxraazgjctfsgj2hkwy

A case study of intended versus actual experience of adaptivity in a tangible storytelling system

Karen Tanenbaum, Marek Hatala, Theresa Tanenbaum, Ron Wakkary, Alissa Antle
2013 User modeling and user-adapted interaction  
The recommendation engine can be run in three different configurations to examine the effects of different adaptive methods.  ...  The Reading Glove is an interactive storytelling system featuring a wearable, glove-based interface and a set of narratively rich objects.  ...  Adaptivity in the Reading Glove The core adaptive component in the Reading Glove is the recommender system displayed on the tabletop screen.  ... 
doi:10.1007/s11257-013-9140-9 fatcat:a4dvceihdvcjvfpgfpob22qdku

Embedding Emotional Context in Recommender Systems

Gustavo Gonzalez, Josep Lluis de la Rosa, Miquel Montaner, Sonia Delfin
2007 2007 IEEE 23rd International Conference on Data Engineering Workshop  
We first introduce Ambient Recommender Systems, which arise from the analysis of new trends on the exploitation of the emotional context in the next generation of recommender systems.  ...  While most approaches to recommending have focused on algorithm performance, SPA makes recommendations to users on the basis of emotional information acquired in an incremental way.  ...  Update stage: this stage keeps the SUM informed of user changes according to recent interactions based on reward and punish mechanisms.  ... 
doi:10.1109/icdew.2007.4401075 dblp:conf/icde/GonzalezRMD07 fatcat:oeq5jscehfakhnkrnlevibvhoe

AutoML for Deep Recommender Systems: A Survey [article]

Ruiqi Zheng, Liang Qu, Bin Cui, Yuhui Shi, Hongzhi Yin
2022 arXiv   pre-print
However, the design of deep recommender systems heavily relies on human experiences and expert knowledge.  ...  Recommender systems play a significant role in information filtering and have been utilized in different scenarios, such as e-commerce and social media.  ...  There are two stages for AutoFIS: search stage and re-train stage.  ... 
arXiv:2203.13922v2 fatcat:awvhxzkopfcafgryusmjl4davu
« Previous Showing results 1 — 15 out of 620,457 results