دانلود و نمایش مقالات مرتبط با Social networks::صفحه 1
دانلود بهترین مقالات isi همراه با ترجمه فارسی
نتیجه جستجو - Social networks

تعداد مقالات یافته شده: 326
ردیف عنوان نوع
1 Towards a distributed local-search approach for partitioning large-scale social networks
به سمت یک جستجوی محلی توزیع شده برای پارتیشن بندی شبکه های اجتماعی در مقیاس بزرگ-2020
Large-scale social graph data poses significant challenges for social analytic tools to mon- itor and analyze social networks. A feasible solution is to parallelize the computation and leverage distributed graph computing frameworks to process such big data. However, it is nontrivial to partition social graphs into multiple parts so that they can be computed on distributed platforms. In this paper, we propose a distributed local search algorithm, named dLS, which enables quality and efficient partition of large-scale social graphs. With the vertex-centric computing model, dLS can achieve massive parallelism. We employ a distributed graph coloring strategy to differentiate neighbor nodes and avoid interference during the parallel execution of each vertex. We convert the original graph into a small graph, Quotient Network , and obtain local search solution from processing the Quotient Net- work , thus further improving the partition quality and efficiency of dLS. We have evaluated the performance of dLS experimentally using real-life and synthetic social graphs, and the results show that dLS outperforms two state-of-the-art algorithms in terms of partition quality and efficiency.
Keywords: Graph partitioning | Social network | Local search algorithm
مقاله انگلیسی
2 Securing instant messaging based on blockchain with machine learning
ایمن سازی پیام های فوری بر اساس blockchain با یادگیری ماشین-2019
Instant Messaging (IM) offers real-time communications between two or more participants on Internet. Nowadays, most IMs take place on mobile applications, such as WhatsApp, WeChat, Viber and Facebook Messenger, which have more users than social networks, such as Twitter and Facebook. Among the applications of IMs, online shopping has become a part of our everyday life, primarily those who are busiest. However, transaction disputes are often occurred online shopping. Since most IMs are centralized and message history is not stored in the center, the messaging between users and owners of online shops are not reliable and traceable. In China, online shopping sales have soared from practically zero in 2003 to nearly 600 hundred million dollars last year, and now top those in the United States. It is very crucial to secure the instant messaging in online shopping in China. We present techniques to exploit blockchain and machine learning algorithms to secure instant messaging. Since the cryptography of Chinese national standard is encouraged to adopt in security applications of China, we propose a blockchain-based IM scheme with the Chinese cryptographic bases. First, we design a message authentication model based on SM2 to avoid the counterfeit attack and replay attack. Second, we design a cryptographic hash mode based on SM3 to verify the integrity of message. Third, we design a message encryption model based on SM4 to protect the privacy of users. Besides, we propose a method based on machine learning algorithms to monitor the activity on blockchain to detect anomaly. To prove and verify the blockchain-based IM scheme, a blockchain-based IM system has been designed on Linux platforms. The implementation result shows that it is a practical and secure IM system, which can be applied to a variety of instant messaging applications directly
Keywords: Instant Messaging (IM) | BlockChain | Machine learning | Distributed Ledger Technology (DLT) | Safety and security
مقاله انگلیسی
3 استفاده از رسانه های اجتماعی برای شناسایی جذابیت گردشگری در شش شهر ایتالیا
سال انتشار: 2019 - تعداد صفحات فایل pdf انگلیسی: 7 - تعداد صفحات فایل doc فارسی: 18
تکامل فناوری و گسترش شبکه های اجتماعی به افراد اجازه داده است که مقادیر زیادی داده را در هر روز تولید کنند. شبکه های اجتماعی کاربرانی را فارهم می کند که به اطلاعات دسترسی دارند. هدف این مقاله تعیین جذابیت های شهرهای مختلف گردشگری ازطریق بررسی رفتار کاربران در شبکه های اجتماعی می باشد. پایگاه داده ای شامل عکس های جغرافیایی واقع شده در شش شهر می باشد که به عنوان یک مرکز فرهنگی و هنری در ایتالیا عمل می کنند. عکس ها از فلیکر که یک بستر به اشتراک گذاری داده می باشد دانلود شدند. تحلیل داده ها با استفاده از دیدگاه مدلهای یادگیری ریاضی و ماشینی انجام شد. نتایج مطالعه ما نشانگر نقشه های شناسایی رفتار کاربران، گرایش سالانه به فعالیت تصویری در شهرها و تاکید بر سودمند بودن روش پیشنهادی می باشد که قادر به تامین اطلاعات مکانی و کاربری است. این مطالعه تاکید می کند که چگونه تحلیل داده های اجتماعی می تواند یک مدل پیشگویانه برای فرموله کردن طرح های گردشگری خلق کند. در انتها، راهبردهای عمومی بازاریابی گردشگری مورد بحث قرار می گیرند.
مقاله ترجمه شده
4 تعلق خاطر و شبکه های اجتماعی
سال انتشار: 2019 - تعداد صفحات فایل pdf انگلیسی: 4 - تعداد صفحات فایل doc فارسی: 13
مقاله حاضر دو خط تحقیقی را پوشش می دهد که تعلق خاطر و شبکه های اجتماعی را به هم مرتبط می کند. یک نفر روی شبکه های تعلق خاطر تمرکز می کند (افرادی که نیازهای تعلق خاطر یک شخص را برآورده می کنند) و تفاوت های مربوط به ترکیب و سن و سال را در رابطه با این شبکه ها بررسی می کند. یکی دیگر تعلق خاطر را با تحلیل شبکه های اجتماعی ادغام می کند تا بررسی کند که چگونه تفاوت های فردی در تعلق خاطر بزرگسالان با مدیریت و ویژگی های شبکه های اجتماعی مثل تراکم، چندگانگی و مرکزیت مرتبط است. ما نشان می دهیم که شبکه های تعلق خاطر اکثر افراد کوچک و سلسله مراتبی است و یک شخص برای این تعلق خاطر عاملی اساسی می باشد (اغلب یک مادر یا شریک عشقی، بسته به سن). به علاوه، شیوه تعلق خاطر ویژگی ها و مدیریت شبکه را پیش بینی می کند به گونه ای که ناامنی با بسته نزدیکی، چندگانگی و مرکزیت کمتر و مدریت ضعیف تر (حفظ کمتر، فروپاشی بیشتر) همراه است.
مقاله ترجمه شده
5 An efficient manifold regularized sparse non-negative matrix factorization model for large-scale recommender systems on GPUs
یک مدل فاکتور گیری ماتریس غیر منفی خلوت منظم شده چند ظرفیتی کارا برای سیستمهای توصیه گر در مقیاس بزرگ بر روی GPU-2019
Article history:Received 31 January 2018Revised 1 July 2018Accepted 25 July 2018Available online 27 July 2018Keywords:Collaborative filtering recommender systemsData miningEuclidean distance and KL-divergence GPU parallelizationManifold regularizationNon-negative matrix factorizationNon-negative Matrix Factorization (NMF) plays an important role in many data mining ap- plications for low-rank representation and analysis. Due to the sparsity that is caused by missing information in many high-dimension scenes, e.g., social networks or recommender systems, NMF cannot mine a more accurate representation from the explicit information. Manifold learning can incorporate the intrinsic geometry of the data, which is combined with a neighborhood with implicit information. Thus, manifold-regularized NMF (MNMF) can realize a more compact representation for the sparse data. However, MNMF suffers from (a) the forming of large-scale Laplacian matrices, (b) frequent large-scale matrix ma- nipulation, and (c) the involved K-nearest neighbor points, which will result in the over- writing problem in parallelization. To address these issues, a single-thread-based MNMF model is proposed on two types of divergence, i.e., Euclidean distance and Kullback–Leibler (KL) divergence, which depends only on the involved feature-tuples’ multiplication and summation and can avoid large-scale matrix manipulation. Furthermore, this model can remove the dependence among the feature vectors with fine-grain parallelization inher- ence. On that basis, a CUDA parallelization MNMF (CUMNMF) is presented on GPU com- puting. From the experimental results, CUMNMF achieves a 20X speedup compared with MNMF, as well as a lower time complexity and space requirement.© 2018 Published by Elsevier Inc.
Keywords: Collaborative filtering recommender systems | Data mining | Euclidean distance and KL-divergence | GPU parallelization | Manifold regularization | Non-negative matrix factorization
مقاله انگلیسی
6 SOS: A multimedia recommender System for Online Social networks
SOS: یک سیستم توصیه گر چندرسانه ای برای شبکه های اجتماعی آنلاین-2019
The use of Online Social Networks has been rapidly increased over the last years. In particular, Social Media Networks allow people to communicate, share, comment and observe different types of multimedia content. This phenomenon produces a huge amount of data showing Big Data features, mainly due to their high change rate, large volume and intrinsic heterogeneity. In this perspective, in the last decade Recommender Systems have been introduced to support the browsing of such data collections, assisting users to find ‘‘what they really need’’ within this ocean of information. In this research work, we propose and describe a novel recommending system for big data applications able to provide recommendations on the base of the interactions among users and the generated multimedia contents in one or more social media networks. The proposed system relies on a ‘‘user-centered’’ approach. An experimental campaign, using data coming from many social media networks, has been performed in order to assess the proposed approach also showing how it can obtain very promising results
Keywords: Recommender Systems | Online Social Networks | Collaborative and Content-based filtering
مقاله انگلیسی
7 TruGRC: Trust-Aware Group Recommendation with Virtual Coordinators
TruGRC: توصیه گروه اعتماد به نفس با هماهنگ کنندگان مجازی-2019
In recent years, an increase in group activities on websites has led to greater demand for highly-functional group recommender systems. The goal of group recommendation is to capture and distill the preferences of each group member into a single recommendation list that meets the needs of all group members. Existing aggregation functions perform well in harmonious and congruent scenarios, but tend not to generate satisfactory results when group members hold conflicting preferences. Moreover, most of current studies improve group recommendation only based on a single aggregation strategy and explicit trust information is still ignored in group recommender systems. Motivated by these concerns, this paper presents TruGRC, a novel Trust-aware Group Recommendation method with virtual Coordinators, that combines two different aggregation strategies: result aggregation and profile aggregation. As each individual’s preferences are modeled, a virtual user is built as a coordinator to represent the profile aggregation strategy. This coordinator provides a global view of the preferences for all group members by interacting with each user to resolve conflicting preferences. Then, we also model the impact from group members to the virtual coordinator in accordance with personal social influence inferred by trust information on social networks. Group preferences can be easily generated by the average aggregation method under the effect of the virtual coordinator. Experimental results on two benchmark datasets with a range of different group sizes show that TruGRC method has significant improvements compared to other state-of-the-art methods
Keywords: Group recommendation | Recommender systems | Virtual coordinators | Trust
مقاله انگلیسی
8 درآوردن شبکه های اجتماعی دارای مقیاس آزاد از حالت بی نامی با استفاده از روش قسمت بندی طیفی
سال انتشار: 2019 - تعداد صفحات فایل pdf انگلیسی: 5 - تعداد صفحات فایل doc فارسی: 15
داده های شبکه های اجتماعی به صورت گسترده ای با بخشهای ثالث به اشتراک گذاشته می شوند، ارسال می شوند و منتشر می شوند که منجر به ایجاد خطر افشای اطلاعات محرمانه می شود. اگرچه تامین کننده شبکه همیشه قبل از انتشار آن نگران داده ها می باشد اما حمله کننده ها می توانند هنوزهم داده های بی نام را برطبق اطلاعات کمکی جمع آوری شده بازیابی کنند. ما در این مقاله مشکل از حالت بی نام درآوردن را به مشکل هماهنگ سازی گره در گراف تبدیل می کنیم و روش درآوردن از حالت بی نامی می تواند تعداد گره هایی که باید در هر بار هماهنگ سازی شوند را کاهش می دهد. به علاوه، ما از روش قسمت بندی طیفی برای تقسیم بندی گراف اجتماعی به زیرگراف های گسسته استفاده می کنیم و این روش می تواند به صورت موثری برای شبکه های اجتماعی دارای مقیاس بزرگ به کار برده شود و به صورت موازی با استفاده از چندین پردازشگر اجرا شود. درطی تحلیل تاثیر توزیع قانون توانی روی درآوردن از حالت بی نامی، ما از روی قواعد ترکیبی اطلاعات ساختاری و فردی کاربران را بررسی می کنیم که این کار اطلاعات مشخصه کاربر را عملی تر می سازد.
مقاله ترجمه شده
9 Fuzzy Group Decision Making for influence-aware recommendations
تصمیم گیری گروه فازی برای توصیه های نفوذ-آگاه-2019
Group Recommender Systems are special kinds of Recommender Systems aimed at suggesting items to groups rather than individuals taking into account, at the same time, the preferences of all (or the majority of) members. Most existing models build recommendations for a group by aggregating the preferences for their members without taking into account social aspects like user personality and interpersonal trust, which are capable of affecting the item selection process during interactions. To consider such important factors, we propose in this paper a novel approach to group recommendations based on fuzzy influence-aware models for Group Decision Making. The proposed model calculates the influence strength between group members from the available information on their interpersonal trust and personality traits (possibly estimated from social networks). The estimated influence network is then used to complete and evolve the preferences of group members, initially calculated with standard recommendation algorithms, toward a shared set of group recommendations, simulating in this way the effects of influence on opinion change during social interactions. The proposed model has been experimented and compared with related works
Keywords: Recommender systems | Group Decision Making | Social influence
مقاله انگلیسی
10 A compositional model of multi-faceted trust for personalized item recommendation
یک مدل ترکیبی از اعتماد چند جانبه برای توصیه کالای شخصی-2019
Trust-based recommender systems improve rating prediction with respect to Collaborative Filtering by leveraging the additional information provided by a trust network among users to deal with the cold start problem. However, they are challenged by recent studies according to which people generally per- ceive the usage of data about social relations as a violation of their own privacy. In order to address this issue, we extend trust-based recommender systems with additional evidence about trust, based on public anonymous information, and we make them configurable with respect to the data that can be used in the given application domain: 1. We propose the Multi-faceted Trust Model (MTM) to define trust among users in a compositional way, possibly including or excluding the types of information it contains. MTM flexibly integrates social links with public anonymous feedback received by user profiles and user contributions in social networks. 2. We propose LOCABAL + , based on MTM, which extends the LOCABAL trust-based recommender system with multi-faceted trust and trust-based social regularization. Experiments carried out on two public datasets of item reviews show that, with a minor loss of user cov- erage, LOCABAL + outperforms state-of-the art trust-based recommender systems and Collaborative Filter- ing in accuracy, ranking of items and error minimization both when it uses complete information about trust and when it ignores social relations. The combination of MTM with LOCABAL + thus represents a promising alternative to state-of-the-art trust-based recommender systems.
Keywords: Multi-faceted trust | Trust-based recommender systems | Compositional trust model | Matrix factorization
مقاله انگلیسی
rss مقالات ترجمه شده rss مقالات انگلیسی rss کتاب های انگلیسی rss مقالات آموزشی