检索结果-内蒙古大学图书馆

DPM: A novel distributed large-scale social graph processing framework for link prediction algorithms

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2018年第Part1期78卷 474-480页

作者： Corbellini, Alejandro Godoy, Daniela Mateos, Cristian Schiaffino, Silvia Zunino, Alejandro UNICEN ISISTAN CONICET Paraje Arroyo Seco Campus Univ RA-7000 Buenos Aires DF Argentina

Large-scale graphs have become ubiquitous in social media. Computer-based recommendations in these huge graphs pose challenges in terms of algorithm design and resource usage efficiency when processing recommendations in distributed computing environments. Moreover, recommendation algorithms for graphs, particularly link prediction algorithms, have different requirements depending of the way the underlying graph is traversed. Path-based algorithms usually perform traversals in different directions to build a large ranking of vertices to recommend, whereas random walk-based algorithms build an initial subgraph and perform several iterations on those vertices to compute the final ranking. In this work, we propose a distributed graph processing framework called Distributed Partitioned Merge (DPM), which supports both types of algorithms and we compare its performance and resource usage w.r.t. two relevant frameworks, namely Fork-Join and Pregel. In our experiments, we show that in most tests DPM outperforms both Pregel and Fork-Join in terms of recommendation time, with a minor penalization in network usage in some scenarios. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Distributed graph processing recommendation algorithms Online Social Networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Explainable recommendations: Integrating Reason Generation and Rating Prediction through Multi-Task Learning

引用

APPLIED SCIENCES-BASEL 2024年第18期14卷 8303页

作者： Zhu, Xingyu Xia, Xiaona Wu, Yuheng Zhao, Wenxu Qufu Normal Univ Sch Comp Sci Rizhao 276826 Peoples R China Qufu Normal Univ Fac Educ Qufu 273165 Peoples R China Qufu Normal Univ Chinese Acad Educ Big Data Qufu 273165 Peoples R China

In recent years, recommender systems-which provide personalized recommendations by analyzing users' historical behavior to infer their preferences-have become essential tools across various domains, including e-commerce, streaming media, and social platforms. Recommender systems play a crucial role in enhancing user experience by mining vast amounts of data to identify what is most relevant to users. Among these, deep learning-based recommender systems have demonstrated exceptional recommendation performance. However, these "black-box" systems lack reasonable explanations for their recommendation results, which reduces their impact and credibility. To address this situation, an effective strategy is to provide a personalized textual explanation along with the recommendation. This approach has received increasing attention from researchers because it can enhance users' trust in recommender systems through intuitive explanations. In this context, our paper introduces a novel explainable recommendation model named GCLTE. This model integrates Graph Contrastive Learning with transformers within an Encoder-Decoder framework to perform rating prediction and reason generation simultaneously. In addition, we cleverly combine the neural network layer with the transformer using a straightforward information enhancement operation. Finally, our extensive experiments on three real-world datasets demonstrate the effectiveness of GCLTE in both recommendation and explanation. The experimental results show that our model outperforms the top existing models.

关键词： explainable recommendation multi-task learning contrastive learning rating prediction reason generation recommendation algorithms

来源：评论

学校读者我要写书评

暂无评论

A collaborative filtering recommendation method based on TagIEA expert degree model

A collaborative filtering recommendation method based on Tag...

引用

International Journal of Computational Science and Engineering

作者： Li, Weimin Wang, Bin Zou, Jianbo Sheng, Jinfang School of Information Science and Engineering Central South University 932 Lushan South Road Changsha Hunan410083 China Department of Information Science and Engineering Hunan University of Humanities Science and Technology Loudi Hunan China

In recent years, social networking services and e-commerce have been developing rapidly. The research of recommending in e-commerce service mainly focused on using the collaborative filtering algorithm. But the algorithm had the limitations of data sparsity and cold start. This paper presents a model using TagIEA expert degree metrics in the context of social e-commerce services, where tag and expert degree information are integrated into the collaborative filtering algorithm. The comprehensive recommendation based on the TagIEA expert degree can effectively mitigate the problems of cold start and data sparsity. Finally, this paper verifies the effectiveness of the improved collaborative filtering algorithm by experiments. Copyright © 2017 Inderscience Enterprises Ltd.

关键词： Collaborative filtering Electronic commerce Signal filtering and prediction Social networking (online) Telecommunication services Collaborative filtering algorithms Collaborative filtering recommendations Data sparsity E commerce services Expert degree recommendation algorithms SNSs Social networking services

来源：评论

学校读者我要写书评

暂无评论

Cornac: A Comparative Framework for Multimodal Recommender Systems

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2020年第1期21卷 1-5页

作者： Salah, Aghiles Quoc-Tuan Truong Lauw, Hady W. Singapore Management Univ Sch Informat Syst 80 Stamford Rd Singapore 178902 Singapore

Cornac is an open-source Python framework for multimodal recommender systems. In addition to core utilities for accessing, building, evaluating, and comparing recommender models, Cornac is distinctive in putting emphasis on recommendation models that leverage auxiliary information in the form of a social network, item textual descriptions, product images, etc. Such multimodal auxiliary data supplement user-item interactions (e.g., ratings, clicks), which tend to be sparse in practice. To facilitate broad adoption and community contribution, Cornac is publicly available at https://***/PreferredAI/cornac, and it can be installed via Anaconda or the Python Package Index (pip). Not only is it well-covered by unit tests to ensure code quality, but it is also accompanied with a detailed documentation(1), tutorials, examples, and several built-in benchmarking data sets.

关键词： comparison multimodality recommendation algorithms software

来源：评论

学校读者我要写书评

暂无评论

The Automation of Taste: A Theoretical Exploration of Mobile ICTs and Social Robots in the Context of Music Consumption

引用

INTERNATIONAL JOURNAL OF SOCIAL ROBOTICS 2015年第3期7卷 407-416页

作者： Barile, Nello Sugiyama, Satomi Univ Milan IULM I-20143 Milan Italy Franklin Univ Switzerland CH-6924 Lugano Switzerland

Today robotics and robotic functions are increasingly relevant to our everyday life. Although the notion of social robots tends to trigger the idea of autonomous machines such as humanoid and zoomorphic robots, it can be extended to include information and communication technologies (ICTs) Sugiyama and Vincent (Intervalla Platf Intellect Exch 1:1-6, 2013). The present paper seeks to describe the implications of the deepest penetration of mobile ICTs in everyday life through the proliferation of technologies as well as the cogent effect of software and new applications controlled by algorithms. As smart phones and wearable devices continue to evolve and come closer to the human body, and also, transform from "a hard and utilitarian conception to a softer ideal based on the emotional value of new devices" Barile (Intervalla Platf Intellect Exch 1:101-115, 2013, p. 102), this is an important and timely question to examine. In particular, this paper considers how mobile ICTs such as smart phones have the power to shape, and furthermore, to "automate" our emotions and taste by exploring the examples of widely-adopted music applications. By reviewing some of the classic theories of taste and the current technological environment of music consumption, it proposes the notion of "the automation of taste," which is a theoretical framework that can describe the new role of the technological mediation in the social definition of taste, considering the music recommendation systems as a sort of automatized cognitive environment. The paper argues that the automation of taste, facilitated by the smart phone and its applications and algorithms, leads to the human carrying some traces of robots.

关键词： Automation Emotional capitalism Social robot Music Subcultures recommendation algorithms

来源：评论

学校读者我要写书评

暂无评论

Impact of recommender algorithms on the sales of e-commerce websites

引用

INTERNATIONAL JOURNAL OF INNOVATION SCIENCE 2021年第2期13卷 161-174页

作者： Sinha, Manish Srivastava, Divyank SIU SCMHRD Pune Maharashtra India

Purpose - With the current pandemic situation, the world is shifting to online buying and therefore the purpose of this study is to understand how the industry can improve sales based on the product recommendations shown on their online platforms. Design/methodology/approach - This paper has studied content-based filtering using decision trees algorithm and collaborative filtering using K-nearest neighbour algorithm and measured their impact on sales of product of different genres on e-commerce websites and if their recommendation causes a difference in *** paper has conducted a field experiment to analyse the customer frequency, change in sales caused by different algorithms and also tried analysing the change in buying preferences of customers in post-pandemic situation and how this paper can improve on the search results by incorporating them in the already used algorithms. Findings - This study indicates that different algorithms cause differences in sales and score over each other depending upon the category of the product sold. It also suggests that post-Covid, the buying frequency and the preferences of consumers have changed significantly. Research limitations/implications - The study is limited to existing users of these sites, it also requires the sites to have a huge database of active users and products. Also, the preferences and likings of Indian subcontinent might not generally apply everywhere else. Originality/value - This study enables better insight into consumer behaviour, thus enabling the data scientists to design better algorithms and help the companies improve their product sales.

关键词： Sales Insights E-commerce recommendation algorithms

来源：评论

学校读者我要写书评

暂无评论

A hybrid recommendation algorithm based on user comment sentiment and matrix decomposition

引用

INFORMATION SYSTEMS 2023年 117卷

作者： Li, Xiang Jun Deng, Geng Sheng Wang, Xiao Zhen Wu, Xiao Liang Zeng, Qing Wei Nanchang Univ Sch Software Nanchang 330046 Jiangxi Peoples R China Nanchang Univ Sch Math & Comp Sci Nanchang 330031 Peoples R China Nanchang Univ Network Ctr Nanchang 330031 Peoples R China Beijing Chia Tai Investment Co LTD Beijing 100005 Peoples R China

In order to improve recommendation quality of recommendation algorithms, this paper proposes a hybrid recommendation algorithm based on user comments sentiment and matrix decomposition (abbreviate as RACSMD). This algorithm first calculates the sentiment tendency towards the user's comment through the LSTM algorithm, and then integrates the sentiment value of the user's rating to increase the accuracy of the user's actual rating before combining the matrix decomposition recommendation algorithm to improve recommendation quality. This paper theoretically verifies the feasibility of RACSMD through an algorithm example. Moreover, corresponding experimental analysis is conducted on the basis of three data sets of Beeradvocate, Modcloth and Amazon. Experimental results show that the introduction to sentiment tendencies towards user comments can effectively improve recommendation quality of recommendation algorithms.& COPY;2023 Elsevier Ltd. All rights reserved.

关键词： recommendation algorithms Sentiment analysis algorithms LSTM Matrix decomposition technology

来源：评论

学校读者我要写书评

暂无评论

Link recommendations: Their impact on network structure and minorities 22

Link recommendations: Their impact on network structure and ...

引用

14th ACM Web Science Conference (WebSci)

作者： Ferrara, Antonio Espin-Noboa, Lisette Karimi, Fariba Wagner, Claudia GESIS Leibniz Inst Social Sci Cologne Germany Rhein Westfal TH Aachen Aachen Germany Complex Sci Hub Vienna Austria Cent European Univ Vienna Austria

ISBN: (纸本)9781450391917

Network-based people recommendation algorithms are widely employed on the Web to suggest new connections in social media or professional platforms. While such recommendations bring people together, the feedback loop between the algorithms and the changes in network structure may exacerbate social biases. These biases include rich-get-richer effects, filter bubbles, and polarization. However, social networks are diverse complex systems and recommendations may affect them differently, depending on their structural properties. In this work, we explore five people recommendation algorithms by systematically applying them over time to different synthetic networks. In particular, we measure to what extent these recommendations change the structure of bi-populated networks and show how these changes affect the minority group. Our systematic experimentation helps to better understand when link recommendation algorithms are beneficial or harmful to minority groups in social networks. In particular, our findings suggest that, while all algorithms tend to close triangles and increase cohesion, all algorithms except Node2Vec are prone to favor and suggest nodes with high in-degree. Furthermore, we found that, especially when both classes are heterophilic, recommendation algorithms can reduce the visibility of minorities.

关键词： recommendation algorithms friendship recommendations network science social networks homophily preferential attachment

来源：评论

学校读者我要写书评

暂无评论

IGAN: A collaborative filtering model based on Improved Generative Adversarial Networks for recommendation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第1期124卷

作者： Song, Xiaoyuan Qin, Jiwei Ren, Qiulin Zheng, Jiong Xinjiang Univ Sch Informat Sci & Engn Urumqi 830046 Peoples R China Xinjiang Univ Key Lab Signal Detect & Proc Urumqi 830000 Xinjiang Uygur Peoples R China

In recent years, Generative Adversarial Networks (GANs) have been successfully applied to collaborative filtering for implicit feedback. However, the ability of GAN to learn user interest distributions is greatly reduced due to its difficulty in characterizing the features. In this paper, a collaborative filtering model based on Improved Generative Adversarial Networks (IGAN) is proposed to address the above issue. In IGAN, we first introduce the independent encoder and generator to learn features representation during adversarial training. Then, the Kullback-Leibler (KL) loss and reconstruction loss are added as the penalty term to further fit the interest distribution of users and achieve higher recommendation accuracy. Finally, this paper conducts extensive experiments on three real public datasets, showing that the IGAN method has a maximum improvement of 5.26% and 5.43% in P@5 and NDCG@5 compared with the current GAN-based methods.

关键词： Collaborative filtering Generative Adversarial Networks Variational autoencoders recommendation algorithms

来源：评论

学校读者我要写书评

暂无评论

Improving recommendation by connecting user behavior in temporal and topological dimensions

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2022年 585卷

作者： Li, Heyang Zeng, An Beijing Normal Univ Sch Syst Sci Beijing 100875 Peoples R China

The rapid development of Internet provides many high quality data sets for understanding human online behavior patterns. Many analysis tools from complexity science such as complex networks and human dynamics have been applied to study human online activities. However, in most existing works, the topological and temporal features of human online activities are analyzed independently. In this paper, we connect these two dimensions by investigating the relations between online users inter-event time and the network distance between the items selected by users. We find that users will choose items with longer network distance when the inter-event time is long, and vice versa. This finding is then applied to improve the recommendation process where recommendation diversity should be given more weight when users return from a long inactive period. Finally, we use a trade-off between accuracy and complexity to further improve the recommendation algorithms. (C) 2021 Published by Elsevier B.V.

关键词： Power-law distribution Complex networks Behavioral dynamics recommendation algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：