A correlative denoising autoencoder to model social influence for top-N recommender system

In recent years,there are numerous works been proposed to leverage the techniques of deep learning to improve social-aware recommendation performance.In most cases,it requires a larger number of data to train a robust deep learning model,which contains a lot of parameters to fit training data.However,both data of user ratings and social networks are facing critical sparse problem,which makes it not easy to train a robust deep neural network model.Towards this problem,we propose a novel correlative denoising autoencoder(CoDAE)method by taking correlations between users with multiple roles into account to learn robust representations from sparse inputs of ratings and social networks for recommendation.We develop the CoDAE model by utilizing three separated autoencoders to learn user features with roles of rater,truster and trustee,respectively.Especially,on account of that each input unit of user vectors with roles of truster and trustee is corresponding to a particular user,we propose to utilize shared parameters to learn common information of the units that corresponding to same users.Moreover,we propose a related regularization term to learn correlations between user features that learnt by the three subnetworks of CoDAE model.We further conduct a series of experiments to evaluate the proposed method on two public datasets for Top-N recommendation task.The experimental results demonstrate that the proposed model outperforms state-of-the-art algorithms on rank-sensitive metrics of MAP and NDCG.

Social networks, social capital,and the use of information technology in the urban village:A study of community groups in Manchester, England

Underresourced or socially excluded communities in Manchester, England demonstrate active use of information technologies despite continuing digital inequalities.A systematic look at 31 grassroots community groups, at how they use IT and who helps them, reveals possible mechanisms towards a more inclusive network society. Social network and social capital theories help make apparent how people are self-organizing with respect to information technology in ways that reach across ethnicity, class, gender, and generations for skilled help, yet stay close to their strong-tie, bonding-social-capital networks, relying largely on people in their own communities. Based on 25 measures of IT use, the groups fall into three progressively more extensive categories: Downloaders(using computers and the Internet, particularly e-mails), uploaders(maintaining a group web presence), and cyberorganizers(helping others to become uploaders or downloaders). These categories align with each individual group's purpose.

Spatial Management of Distributed Social Systems

The paper describes the use of invented,developed,and tested in different countries of the high-level spatial grasp model and technology capable of solving important problems in large social systems,which may be represented as dynamic,self-evolving and distributed social networks.The approach allows us to find important solutions on a holistic level by spatial navigation and parallel pattern matching of social networks with active self-propagating scenarios represented in a special recursive language.This approach effectively hides inside the distributed and networked language implementation traditional system management routines,often providing hundreds of times shorter and simpler high-level solution code.The paper highlights the demands to efficient simulation of social systems,briefs the technology used,and provides some programming examples for solutions of practical problems.

Tag-Aware Recommender Systems:A State-of-the-Art Survey

In the past decade,Social Tagging Systems have attracted increasing attention from both physical and computer science communities.Besides the underlying structure and dynamics of tagging systems,many efforts have been addressed to unify tagging information to reveal user behaviors and preferences,extract the latent semantic relations among items,make recommendations,and so on.Specifically,this article summarizes recent progress about tag-aware recommender systems,emphasizing on the contributions from three mainstream perspectives and approaches：network-based methods,tensor-based methods,and the topic-based methods.Finally,we outline some other tag-related studies and future challenges of tag-aware recommendation algorithms.

Exploiting Geo-Social Correlations to Improve Pairwise Ranking for Point-of-Interest Recommendation

Recently, as location-based social network(LBSN) rapidly grow, point-of-interest(POI) recommendation has become an important way to help people locate interesting places. Nowadays, there have been deep studies conducted on the geographical and social influence in the point-of-interest recommendation model based on the rating prediction. The fact is, however, relying solely on the rating fails to reflect the user's preferences very accurately, because the users are most concerned with the list of ranked point-of-interests(POIs) on the actual output of recommender systems. In this paper, we propose a co-pairwise ranking model called Geo-Social Bayesian Personalized Ranking model(GSBPR), which is based on the pairwise ranking with the exploiting geo-social correlations by incorporating the method of ranking learning into the process of POI recommendation. In this model, we develop a novel BPR pairwise ranking assumption by injecting users' geo-social preference. Based on this assumption, the POI recommendation model is reformulated by a three-level joint pairwise ranking model. And the experimental results based on real datasets show that the proposed method in this paper enjoys better recommendation performance compared to other state-of-the-art POI recommendation models.

Recommending Friends Instantly in Location-based Mobile Social Networks

Differently from the general online social network(OSN),locationbased mobile social network(LMSN),which seamlessly integrates mobile computing and social computing technologies,has unique characteristics of temporal,spatial and social correlation.Recommending friends instantly based on current location of users in the real world has become increasingly popular in LMSN.However,the existing friend recommendation methods based on topological structures of a social network or non-topological information such as similar user profiles cannot well address the instant making friends in the real world.In this article,we analyze users' check-in behavior in a real LMSN site named Gowalla.According to this analysis,we present an approach of recommending friends instantly for LMSN users by considering the real-time physical location proximity,offline behavior similarity and friendship network information in the virtual community simultaneously.This approach effectively bridges the gap between the offline behavior of users in the real world and online friendship network information in the virtual community.Finally,we use the real user check-in dataset of Gowalla to verify the effectiveness of our approach.

Potential friendship discovery in social networks based on hybrid ensemble multiple collaborative filtering models in a 5G network environment

At present, 5G network technology is being applied to various social network modes, and it can provide technical and traffic support for social networks. Potential friendship discovery technology in 5G-enabled social networks is beneficial for users to make potential friends and expand their range of activities and social hierarchy, which is highly sought after in today's social networks and has great economic and application value. However, the sparsity of the dominant user association dataset in 5G-enabled social networks and the limitations of traditional collaborative filtering algorithms are two major challenges for the friend recommendation problem. Therefore, in order to overcome these problems regarding previous models, we propose a Hybrid Ensemble Multiple Collaborative Filtering Model (HEMCF) for discovering potential buddy relationships. The HEMCF model draws on a special autoencoder method that can effectively exploit the association matrix between friends and additional information to extract a hidden representation of users containing global structural information. Then, it uses the random walk-based graph embedding algorithm DeepWalk to extract another hidden representation of users in the buddy network containing local structural information. Finally, in the output module, the HEMCF model stacks and multiplies the two types of hidden representations of users to ensure that the information mentioned above is concentrated in the final output to generate the final prediction value. The magnitude of the prediction value represents the probability of the users being friends, with larger values representing a high probability of the two users being friends, and vice versa. Experimental results show that the proposed method boosts the accuracy of the relationship prediction over baselines on 3 real-world public datasets dramatically.

Methods for Measuring Diffusion of a Social Media-Based Health Intervention

This study evaluated the feasibility of measuring diffusion from a social networking community-level intervention. One year after completion of a randomized controlled HIV prevention trial on Facebook, 112 minority men who have sex with men (MSM) were asked to refer African-American and/or Latino sex partners to complete a survey. Results suggest that, compared to non-referrers, referrers spent more time online, controlling for age, race, education, and condition. Over 60% of referrals reported hearing about the intervention, and over half reported that the referrer talked to them about changing health behaviors. Results provide support and initial feasibility of using social networking for diffusing community-based HIV interventions.

Recommending Who to Follow on Twitter Based on Tweet Contents and Social Connections

In this paper, we examine methods that can provide accurate results in a form of a recommender system within a social networking framework. The social networking site of choice is Twitter, due to its interesting social graph connections and content characteristics. We built a recommender system which recommends potential users to follow by analyzing their tweets using the CRM114 regex engine as a basis for content classification. The evaluation of the recommender system was based on a dataset generated from real Twitter users created in late 2009.

Recommending Personalized POIs from Location Based Social Network

Location based social networks（ LBSNs） provide location specific data generated from smart phone into online social networks thus people can share their points of interest（ POIs）. POI collections are complex and can be influenced by various factors,such as user preferences,social relationships and geographical influence. Therefore,recommending new locations in LBSNs requires to take all these factors into consideration. However,one problem is how to determine optimal weights of influencing factors in an algorithm in which these factors are combined. The user similarity can be obtained from the user check-in data,or from the user friend information,or based on the different geographical influences on each user＇s check-in activities. In this paper,we propose an algorithm that calculates the user similarity based on check-in records and social relationships,using a proposed weighting function to adjust the weights of these two kinds of similarities based on the geographical distance between users. In addition,a non-parametric density estimation method is applied to predict the unique geographical influence on each user by getting the density probability plot of the distance between every pair of user＇s check-in locations. Experimental results,using foursquare datasets,have shown that comparisons between the proposed algorithm and the other five baseline recommendation algorithms in LBSNs demonstrate that our proposed algorithm is superior in accuracy and recall,furthermore solving the sparsity problem.

A Personalized Recommendation Algorithm with User Trust in Social Network

In the era of big data, personalized recommendation has become an important research issue in social networks as it can find and match user’s preference. In this paper, the user trust is integrated into the recommendation algorithm, by dividing the user trust into 2 parts: user score trust and user preference trust. In view of the common items in user item score matrix, the algorithm combines the number of items with the score similarity between users, and establishes an asymmetric trust relationship matrix so as to calculate the user’s score trust. For the non common score items, we use the attribute information of items and the scoring weight to calculate the user’s preference trust. Based on the user trust in social network, a new collaborative filtering recommendation algorithm is proposed. Besides, a new matrix factorization recommendation algorithm is proposed by combining the user trust with matrix factorization. We did the experiments comparing with the related algorithms on the real data sets of social network. The results show that the proposed algorithms can effectively improve the accuracy of recommendation.

“一带一路”共建国家农业科技创新合作网络结构演化及影响因素探究

基于WOS数据库中跨国农业科技论文合著数据,借助社会网络分析法和QAP回归模型,剖析2006—2020年“一带一路”共建国家农业科技创新合作网络结构演化特征及影响因素。研究发现:(1)“一带一路”共建国家农业科技创新合作网络整体结构指标均得到了不同程度的优化,且各指标优化速度快于全球农业科技创新合作网络。(2)“一带一路”共建国家和全球国家农业科技创新合作网络去中心化趋势均较明显,多核共存特征更加突出。(3)中国和意大利在合作网络中同时扮演着核心者和中间人角色。(4)合作网络呈现出双向溢出、主受益、“经纪人”3种类型的块集聚特征,亚洲国家是推动农业科技创新合作的主引擎。(5)制度、经济、科研和认知邻近对3个阶段的合作网络都具有显著的正向影响,而空间邻近对合作的阻碍作用逐渐减弱。“一带一路”共建国家应进一步重视跨国农业科技创新合作,明确自身在合作网络中的地位与角色,充分借助网络核心国家的重要作用,加速融入农业科技创新国际合作核心网络.

“一带一路”共建国家间的技术扩散——基于技术内容与网络结构的分析

技术扩散是强化国际经济与创新联系的有效途径,是构建高质量开放创新体系的重要方式。国际技术扩散作为两个主体间的技术扩散活动具有方向性,不同国家的创新政策和技术发展战略侧重点不同,在技术扩散能力和技术吸收能力上均有差异。因而国家间需要构建高效、稳定的技术扩散网络,充分发挥自身的技术优势、补齐技术短板,进一步加大技术流动和增强创新能力。本研究基于技术扩散理论,运用专利引证数据构建“一带一路”共建国家间技术扩散网络,分时段纵向分析共建国家技术扩散网络的演化,分技术领域横向分析共建国家间技术扩散的特征,探索中国与共建国家间技术扩散的内容和路径。研究认为:中国在共建国家技术扩散网络中的核心地位逐步确立,且在“一带一路”倡议提出后中国的核心位置更加明显、技术扩散范围更加广泛;但整体技术扩散网络密度低,除中国外的其他国家间技术扩散关系构建较少;不同技术领域的技术扩散网络形态各有不同,其中化学技术领域的技术扩散最活跃、网络复杂度最高;俄罗斯在化学、机械工程、仪器、其他技术领域具有一定技术优势,并且对中国的技术扩散强度很大,而中国在电气工程技术领域更有技术扩散优势。

基于组织-技术依存网络的技术融合机理

技术融合能够显著提高企业的创新能力,对技术融合机理的深入探索有助于选择合适的创新伙伴和融合技术。构建依存型网络分析模型,探究技术特征和技术依附的组织特征与技术融合的关系,并对人工智能产业进行实证研究。研究表明:吸收能力强或扩散能力强的技术容易吸收或流向其他技术;技术成熟度高、技术邻近性强的两种技术容易发生双向流动;被多个组织拥有的共性技术不容易吸收其他技术,但容易流向其他技术,单个组织内拥有的技术间容易发生双向流动。

面向多视图融合的用户一致性社交推荐

针对传统社交推荐准确率不高的问题,提出一种基于多视图融合的用户一致性社交推荐模型。该社交推荐模型考虑到社交网络中用户的不一致性和单一视图信息对推荐结果的影响,使用注意力机制动态过滤出不一致的社交邻居,并结合用户-项目交互信息来学习用户特征表达;同时从知识图谱(knowledge graph,KG)、用户-项目历史交互信息等多个视图学习项目在低维空间的特征表示;最后将用户和项目的特征表示进行内积操作,从而完成最终的推荐任务。为了验证推荐算法的有效性,在Douban和Yelp两个公开的数据集上与六个基线模型进行对比实验,并采用召回率、归一化折损累计增益(normalized discounted cumulative gain,NDCG)和精确率作为评估指标,实验结果表明,所提出的社交推荐模型的性能优于其他模型。

科技创新新型举国体制下多元投资主体网络关联模式

科技创新新型举国体制是应对错综复杂国际环境和全面建成社会主义现代化强国使命任务的重大制度安排,厘清科技创新新型举国体制的多元投资主体关系对于推动有为政府与有效市场相结合具有重要意义。本文在分析科技创新新型举国体制的制度创新基础上,归纳不同实践场景下多元投资主体的基本格局,利用社会网络分析的网络拓扑结构、中心性、核心边缘分析和密度分析手段,对多元投资主体的网络结构、网络中心度以及网络的整体特征进行研究。结果表明,科技创新新型举国体制能充分调动市场与社会力量,各投资主体之间的信息、资源等流动加快,各投资主体间的联系更加紧密,企业在科技创新新型举国体制中将发挥更重要的作用。

基于动态邻域采样的社交推荐模型

基于图神经网络的社交推荐模型在提升推荐系统性能方面有不错的表现。但现有方法都忽略了被查询的目标用户和项目节点与其邻居节点间可能存在特征不匹配的问题,导致噪声的引入而降低了模型性能。为了解决该问题,文中提出一种社交推荐模型DNSSR。首先构建一个包含用户和项目多元关系的关系图谱,图节点间信息关联更丰富;然后利用动态邻域采样机制获得与目标查询对的特征更一致的邻居节点,减少了噪声信息;另外,为了进一步提高模型预测性能,设计了一种增强型图神经网络对采样后得到的关系子图进行建模,它可以区分不同邻居节点的重要性并选择更可靠的信息源,获得更鲁棒的用户和项目嵌入向量用于评分预测。实验结果表明:相比其他先进模型,该模型预测误差明显降低,证明了文中所提各项方法的有效性;尤其是动态邻域采样机制,若将其弃用,DNSSR在Ciao数据集上的RMSE(均方根误差)和MAE(平均绝对误差)指标将分别上升6.05%和7.31%,在Epinions数据集上则分别上升3.49%和5.41%,充分验证了其能有效降低噪声干扰、提高社交推荐模型的性能。

融合用户社交关系的自适应图卷积推荐算法

为了缓解推荐系统中不同用户社交空间与兴趣空间的内在信息差异和忽视高阶邻居的问题,提出了一种融合用户社交关系的自适应图卷积推荐算法(adaptive graph convolutional recommendation algorithm integrating user social relationships,AGCRSR)。首先,模型在嵌入层使用映射矩阵将初始特征向量转换为自适应嵌入;其次,引入注意力机制聚合不同方面的用户嵌入,通过图卷积网络来线性学习用户和项目的潜在表示;最后,通过自适应模块聚合用户表示并利用内积函数预测用户对项目的最终推荐结果。在数据集LastFM和Ciao上与其他基线算法进行了对比实验,实验结果表明AGCRSR的推荐效果较其他算法有显著提升。

结合用户共同意图及社交关系的群组推荐方法

已有的群组推荐模型,在求解用户表示时大多比较单调且仅简单利用用户间的社交关系,使得用户表示不够准确,并且大都未考虑用户共同意图以及社交关系对群组偏好的影响,导致推荐的项目很难符合用户的需求。基于此,提出一种结合用户共同意图及社交关系的群组推荐模型(GR-UCISI)。首先构造用户-项目交互历史与社交关系相结合的用户意图分离模型,利用图神经网络采集每个用户的用户-项目交互以及社交关系信息,求解用户意图和项目表示;其次利用网络游走算法与K-means聚类算法将用户分组,结合用户群组、用户意图以及群组意图聚合过程获取群组共同意图表示;最后根据群组共同意图表示与项目表示得出群组推荐项目列表。该方法充分考虑到用户的个性以及群组成员间的共性对群组偏好的影响,同时结合社交关系缓解数据稀疏性问题,提升模型性能。实验结果表明,与9个对比模型中推荐效果最好的模型相比,在Gowalla数据集上,GR-UCISI的Precision和NDCG指标值分别提高3.01%和5.26%;在Yelp-2018数据集上,GR-UCISI的Precision和NDCG指标值分别提高2.96%和1.12%。