1,295,118 Hits in 3.7 sec Slates Dataset: A new Sequential Dataset Logging Interactions, allViewed Items and Click Responses/No-Click for Recommender Systems Research [article]

Simen Eide, Arnoldo Frigessi, Helge Jenssen, David S. Leslie, Joakim Rishaug, Sofie Verrewaere
2021 arXiv   pre-print
We present a novel recommender systems dataset that records the sequential interactions between users and an online marketplace.  ...  at each interaction.  ...  The interaction type identifies whether it was a search query or the recommendation system that presented the slate.  ... 
arXiv:2111.03340v1 fatcat:2w6et2aq2zc4dgzjz6zdrsaakm

The Impact of View Histories on Edit Recommendations

Seonah Lee, Sungwon Kang, Sunghun Kim, Matt Staats
2015 IEEE Transactions on Software Engineering  
Our results clearly demonstrate the value of considering both views and edits in systems to recommend files to edit, and results in more accurate, earlier, and more flexible recommendations.  ...  We then conducted a comparative simulation of ROSE and MI using the interaction histories stored in the Eclipse Bugzilla system.  ...  To recommend files to edit by utilizing the records of viewed files, MI mines interaction histories.  ... 
doi:10.1109/tse.2014.2362138 fatcat:m3byd7qsjndxnk6yieatv2hsdy

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 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  ...  We propose Dionysius, a hierarchical graphical model based framework and system for incorporating user interactions into recommender systems, with minimal change to the underlying infrastructure.  ...  Our work can be viewed as bringing together the representational (user profile) and interactional (user interactions) views of context, in the job recommendation setting.  ... 
arXiv:1706.03849v1 fatcat:ww7md2lzxraazgjctfsgj2hkwy

A Survey on Extended MI technique for Edit Recommendation using Hybrid History Mining and Relevance Feedback

2015 International Journal of Science and Research (IJSR)  
To guide programmers, researchers have developed history-based recommendation systems following two approaches either by mining view history or by mining edit history.  ...  Accurate recommendations leads to successful, faster, efficient development, but inaccurate recommendations can lead to inappropriate, missed deadline software development.  ...  Proposed Work To recommend files to edit by using the records of viewed files, MI mines programmer interaction histories that are history database.  ... 
doi:10.21275/v4i11.nov151715 fatcat:hx627zgxwjd7ngseqoks7d25iy

Group-Buying Recommendation for Social E-Commerce [article]

Jun Zhang, Chen Gao, Depeng Jin, Yong Li
2020 arXiv   pre-print
We then develop a graph convolutional network model with multi-view embedding propagation, which can extract the complicated high-order graph structure to learn the embeddings.  ...  Group-buying recommendation for social e-commerce, which recommends an item list when users want to launch a group, plays an important role in the group success ratio and sales.  ...  Meanwhile, the graphs for organizing all behaviors consist of two views, initiator view that contains initiator-item interactions and participant view that contains participant-item interactions.  ... 
arXiv:2010.06848v2 fatcat:ewdu4gbz7zed3pwfzd3mybqwee

System Design to Utilize Domain Expertise for Visual Exploratory Data Analysis

Tristan Langer, Tobias Meisen
2021 Information  
Within the prototype, we present an exemplary use case that demonstrates the usefulness of recommended interactions.  ...  Based on these predictions, the system recommends the sequences with the highest predicted insight to data scientist.  ...  We recommend coherent sequences of interactions (i.e., a sequence of consecutive views) to provide more context to an insight compared to recommendation of single independent views.  ... 
doi:10.3390/info12040140 fatcat:poqm5p662barnkn5iyigor5qtu

Towards Multi-Touch Map Interaction on Tabletops: State of the Art and Design Recommendations [article]

F. Klompmaker, R. Ajaj
2010 Eurographics State of the Art Reports  
We figured out design recommendations that we used for our evaluation prototype called MTMap.  ...  Multi-touch allows intuitive, easy and fast interaction in principle but highly depends on the application type used.  ...  Further on they also recommend an additional 2D view.  ... 
doi:10.2312/egp.20101021 fatcat:ndr7jg7wzngejcantvx4z5wgru

MEDLEY: Intent-based Recommendations to Support Dashboard Composition [article]

Aditeya Pandey, Arjun Srinivasan, Vidya Setlur
2022 arXiv   pre-print
MEDLEY also provides a lightweight direct manipulation interface to configure interactions between views in a dashboard.  ...  The system recommends collections based on these analytic intents, and views and widgets can be selected to compose a variety of dashboards.  ...  MEDLEY's dashboard interaction scenarios based on Figure 1C. (A) An example where a view cannot be used to interactively update other views in the dashboard.  ... 
arXiv:2208.03175v1 fatcat:3xitwsrlrvhbdpavjjrvadbd4m

Learning Item-Interaction Embeddings for User Recommendations [article]

Xiaoting Zhao, Raphael Louca, Diane Hu, Liangjie Hong
2018 arXiv   pre-print
One hallmark of Etsy's shopping experience is the multitude of ways in which a user can interact with an item they are interested in: they can view it, favorite it, add it to a collection, add it to cart  ...  Consequently, a user's recommendations should be based not only on the item from their past activity, but also the way in which they interacted with that item.  ...  One can see that the recommendations for a user who has viewed item ℓ should be different than the recommendations for a user who has already carted item ℓ. Figure 3 : 3 4.1.1 Negative Sampling.  ... 
arXiv:1812.04407v1 fatcat:vqfqm3iwwza7lghjgan2wbztre

Code Edit Recommendation Using a Recurrent Neural Network

Seonah Lee, Jaejun Lee, Sungwon Kang, Jongsun Ahn, Heetae Cho
2021 Applied Sciences  
CERNN forms contexts that maintain the sequence of developers' interactions to recommend files to edit and stops recommendations when the first recommendation becomes incorrect for the given evolution  ...  By recommending files to modify, a code edit recommendation system reduces the developer's navigation time when conducting software evolution tasks.  ...  [1] viewed revision history as a subset of the interaction history in that revision history utilizes edit information for recommendations whereas interaction history utilizes both view information and  ... 
doi:10.3390/app11199286 fatcat:in7twfrkvrh4jb3tm6ndfcaali

Deep Multi-View Learning for Tire Recommendation [article]

Thomas Ranvier, Kilian Bourhis, Khalid Benabdeslem, Bruno Canitia
2022 arXiv   pre-print
Our goal is to use a multi-view learning approach to improve our recommender system and improve its capacity to manage multi-view data.  ...  Our study demonstrates the relevance of using multi-view learning within recommender systems.  ...  This extends the number n of views by n(n−1) 2 interaction views.  ... 
arXiv:2203.12451v1 fatcat:bulihckhxnbjxhos4jtx62l7ym

Evaluation of Visualization by Demonstration and Manual View Specification [article]

Bahador Saket, Alex Endert
2018 arXiv   pre-print
One of the visualization tools implements the manual view specification paradigm (Polestar) and another implements the visualization by demonstration paradigm (VisExemplar).  ...  We present an exploratory study comparing the visualization construction and data exploration processes of people using two visualization tools, each implementing a different interaction paradigm.  ...  demonstration (as well as rendering a view once a recommended mapping is chosen).  ... 
arXiv:1805.02711v1 fatcat:rwlz2iqrz5bfxno56r6cjykdou

Multi-view Intent Disentangle Graph Networks for Bundle Recommendation [article]

Sen Zhao, Wei Wei, Ding Zou, Xianling Mao
2022 arXiv   pre-print
Bundle recommendation aims to recommend the user a bundle of items as a whole.  ...  In the real scenario of bundle recommendation, a user's intent may be naturally distributed in the different bundles of that user (Global view), while a bundle may contain multiple intents of a user (Local  ...  The task of bundle recommendation is to predict the probability of user u potentially interacting with a given bundle never seen before.  ... 
arXiv:2202.11425v2 fatcat:we7jnbzkfjakrjmhz56pqo4j7u

Contrastive Meta Learning with Behavior Multiplicity for Recommendation [article]

Wei Wei and Chao Huang and Lianghao Xia and Yong Xu and Jiashu Zhao and Dawei Yin
2022 arXiv   pre-print
data, such as page view, add-to-favourite and purchase.  ...  Traditional recommendation models usually assume that only a single type of interaction exists between user and item, and fail to model the multiplex user-item relationships from multi-typed user behavior  ...  In our multi-behavior recommendation scenario, let X (𝑘) denote the user-item interaction matrix under the 𝑘-th behavior type (e.g., page view, add-to-favorite, purchase).  ... 
arXiv:2202.08523v1 fatcat:mvx3u5hxkvh2hekxisptmupyp4

Personalized Recommendation in Interactive Visual Analysis of Stacked Graphs

Alejandro Toledo, Kingkarn Sookhanaphibarn, Ruck Thawonmas, Frank Rinaldo
2012 ISRN Artificial Intelligence  
We present a system which combines interactive visual analysis and recommender systems to support insight generation for the user.  ...  Our approach combines a stacked graph visualization with a content-based recommender algorithm, where promising views can be revealed to the user for further investigation.  ...  Methodology To produce recommendations in interactive visual analysis, we based our study on the integration of a stacked graph visualization and a content-based recommender algorithm.  ... 
doi:10.5402/2012/389540 fatcat:at7hkbz7ovabpaefqsd24robne
« Previous Showing results 1 — 15 out of 1,295,118 results