CONTEXTUALIZED RECOMMENDATION BASED ON REALITY MINING FROM MOBILE SUBSCRIBERS

It is difficult to be aware of the personal context for providing a mobile recommendation, because each person's activities and preferences are ambiguous and depend upon numerous unknown factors. In order to solve this problem, we have focused on a reality mining to discover social relationships (e.g., family, friends, etc.) between people in the real world. We have assumed that the personal context for any given person is interrelated with those of other people, and we have investigated how to take into account a person's neighbor's contexts, which possibly have an important influence on his or her personal context. This requires that given a dataset, we have to discover the hidden social networks which express the contextual dependencies between people. In this paper, we propose a semiautomatic approach to build meaningful social networks by repeating interactions with human experts. In this research project, we have applied the proposed system to discover the social networks among mobile subscribers. We have collected and analyzed a dataset of approximately two million people.     

Contextualized mobile recommendation service based on interactive social network discovered from mobile users

Personal context is the most significant information for providing contextualized mobile recommendation services at a certain time and place. However, it is very difficult for service providers to be aware of the personal contexts, because each person’s activities and preferences are very ambiguous and depending on numerous unknown factors. In order to deal with this problem, we have focused on discovering social relationships (e.g., family, friends, colleagues and so on) between people. We have assumed that the personal context of a certain person is interrelated with those of other people, and investigated how to employ his neighbor’s contexts, which possibly have a meaningful influence on his personal context. It indicates that we have to discover implicit social networks which express the contextual dependencies between people. Thereby, in this paper, we propose an interactive approach to build meaningful social networks by interacting with human experts. Given a certain social relation (e.g., isFatherOf), this proposed systems can evaluate a set of conditions (which are represented as propositional axioms) asserted from the human experts, and show them a social network resulted from data mining tools. More importantly, social network ontology has been exploited to consistently guide them by proving whether the conditions are logically verified, and to refine the discovered social networks. We expect these social network is applicable to generate context-based recommendation services. In this research project, we have applied the proposed system to discover the social networks between mobile users by collecting a dataset from about two millions of users.     

On analyzing user preference dynamics with temporal social networks

The preferences adopted by individuals are constantly modified as these are driven by new experiences, natural life evolution and, mainly, influence from friends. Studying these temporal dynamics of user preferences has become increasingly important for personalization tasks in information retrieval and recommendation systems domains. However, existing models are too constrained for capturing the complexity of the underlying phenomenon. Online social networks contain rich information about social interactions and relations. Thus, these become an essential source of knowledge for the understanding of user preferences evolution. In this work, we investigate the interplay between user preferences and social networks over time. First, we propose a temporal preference model able to detect preference change events of a given user. Following this, we use temporal networks concepts to analyze the evolution of social relationships and propose strategies to detect changes in the network structure based on node centrality. Finally, we look for a correlation between preference change events and node centrality change events over Twitter and Jam social music datasets. Our findings show that there is a strong correlation between both change events, specially when modeling social interactions by means of a temporal network.     

基于地域特征和异构社交关系的事件推荐算法研究

近几年,在基于事件的社交网络(EBSNs)服务中,为便于增强用户体验,事件推荐任务一直被广泛研究。本文基于对EBSN中用户行为数据的详细分析,提出了一种新型的融合多种数据特征的潜在因子模型。该模型综合考虑EBSN中两种新型的数据特征: 异构的社交关系特征(线上社交关系+线下社交关系)和用户参与行为的地域性特征。基于真实的Meetup数据集,实验结果表明我们的算法在解决事件推荐问题时比传统的算法有更好的性能。
     

基于时空循环神经网络的下一个兴趣点推荐方法

下一个兴趣点推荐已经成为基于位置的社交网络(location-based social networks,LBSNs)中一个重要任务。现有的模型没有深入考虑相邻签到兴趣点之间的转移时空信息,无法对用户访问下一个兴趣点的长短时间偏好和远近距离偏好进行有效建模。本文通过对循环神经网络(recurrent neural network, RNN)进行扩展,提出一个新的基于会话的时空循环神经网络模型(sesson-based spatial-temporal recurrent neural network, SST-RNN)用于下一个兴趣点推荐。该模型通过设置时间转移矩阵和空间转移矩阵分别对用户的时间和空间偏好信息进行建模,综合考虑连续签到兴趣点的序列信息、时空信息以及用户偏好进行下一个兴趣点推荐。通过在2个真实公开的数据集上进行实验,结果显示本文提出的SST-RNN模型的推荐效果比主流的推荐模型有显著提升。在Foursquare和CA数据集上,ACC@5评价指标分别提升了36.38%和13.81%,MAP评价指标分别提升了30.72%和17.26%。     

基于LSTM的POI个性化推荐框架

近年来,随着基于位置的社会网络（Location-Based Social Network,LBSN）热度的不断增加,为用户推荐下一个POI （Point-Of-Interests）也显得越来越重要.而对应的各种应用搜集到的用户的行为时间、地理、好友以及标签等信息的增多,使得POI推荐变得更加容易.目前针对POI推荐,已经有部分算法提出,但是他们受限于自身的局限性,还都不能很好的解决这个问题,例如,个性化马尔科夫链（Factorizing Personalized Markov Chain,FPMC）、张量分解（Tensor Factorization,TF）、RNN （Recurrent Neural Networks）等.但是,这些模型由于其本身缺陷,都不能完美的糅合POI场景中的所有信息.在这篇文章中,我们扩展了长短时记忆循环神经网络（Long-ShorT Memory recurrent neural networks,LSTM）,提出一种全新的推荐框架POI-LSTM来解决POI推荐问题.POI-LSTM借鉴Embedding的思想,对用户信息、好友关系、POI信息和评论信息进行向量化后,输入到神经网络中,同时利用LSTM捕捉用户的兴趣特征和兴趣的变化趋势,最终能够在不同的输入层拟合社交网络信息和语义信息,同时利用用户历史行为的时间和地理位置信息来为用户推荐下一个兴趣点.     

一种基于位置社交网络融合多种情景信息的兴趣点推荐模型

针对现有位置社交网络兴趣点推荐的研究工作主要集中在挖掘兴趣点的情景信息:时间信息、地理位置和评论信息,其中评论信息对用户偏好的影响尚未充分研究的情况。为此,提出一个统一兴趣点推荐模型,融合了用户偏好模型和上述3种情景信息,其中对用户偏好建模采用基于签到次数的度量方法,同时对评论信息采用基于潜在狄利克雷分配主题模型来挖掘用户偏好。实验结果表明,该模型在推荐准确率等多种评价指标上都取得了更好的结果。     

HOPE: a hybrid deep neural model for out-of-town next POI recommendation

Next Point-of-interest (POI) recommendation has been recognized as an important technique in location-based services, and existing methods aim to utilize sequential models to return meaningful recommendation results. But these models fail to fully consider the phenomenon of user interest drift, i.e. a user tends to have different preferences when she is in out-of-town areas, resulting in sub-optimal results accordingly. To achieve more accurate next POI recommendation for out-of-town users, an adaptive attentional deep neural model HOPE is proposed in this paper for modeling user’s out-of-town dynamic preferences precisely. Aside from hometown preferences of a user, it captures the long and short-term preferences of the user in out-of-town areas using “Asymmetric-SVD” and “TC-SeqRec” respectively. In addition, toward the data sparsity problem of out-of-town preference modeling, a region-based pattern discovery method is further adopted to capture all visitor’s crowd preferences of this area, enabling out-of-town preferences of cold start users to be captured reasonably. In addition, we adaptively fuse all above factors according to the contextual information by adaptive attention, which incorporates temporal gating to balance the importance of the long-term and short-term preferences in a reasonable and explainable way. At last, we evaluate the HOPE with baseline sequential models for POI recommendation on two real datasets, and the results demonstrate that our proposed solution outperforms the state-of-art models significantly.

     

RecAm: a collaborative context-aware framework for multimedia recommendations in an ambient intelligence environment

With an ever-increasing accessibility to different multimedia contents in real-time, it is difficult for users to identify the proper resources from such a vast number of choices. By utilizing the user’s context while consuming diverse multimedia contents, we can identify different personal preferences and settings. However, there is a need to reinforce the recommendation process in a systematic way, with context-adaptive information. The contributions of this paper are twofold. First, we propose a framework, called RecAm, which enables the collection of contextual information and the delivery of resulted recommendation by adapting the user’s environment using Ambient Intelligent (AmI) Interfaces. Second, we propose a recommendation model that establishes a bridge between the multimedia resources, user joint preferences, and the detected contextual information. Hence, we obtain a comprehensive view of the user’s context, as well as provide a personalized environment to deliver the feedback. We demonstrate the feasibility of RecAm with two prototypes applications that use contextual information for recommendations. The offline experiment conducted shows the improvement of delivering personalized recommendations based on the user’s context on two real-world datasets.     

LGA: latent genre aware micro-video recommendation on social media

Social media has evolved into one of the most important channels to share micro-videos nowadays. The sheer volume of micro-videos available in social networks often undermines users’ capability to choose the micro-videos that best fit their interests. Recommendation appear as a natural solution to this problem. However, existing video recommendation methods only consider the users’ historical preferences on videos, without exploring any video contents. In this paper, we develop a novel latent genre aware micro-video recommendation model to solve the problem. First, we extract user-item interaction features, and auxiliary features describing both contextual and visual contents of micro-videos. Second, these features are fed into the neural recommendation model that simultaneously learns the latent genres of micro-videos and the optimal recommendation scores. Experiments on real-world dataset demonstrate the effectiveness and the efficiency of our proposed method compared with several state-of-the-art approaches.     

基于多维社交关系嵌入的深层图神经网络推荐方法

社会化推荐系统通过用户的社会属性信息能缓解推荐系统中数据稀疏性和冷启动问题,从而提高推荐系统的精度。然而大多数社会化推荐方法主要针对单一的社交网络,或对多个社交网络进行线性叠加,使得用户社会属性难以充分参与计算,因而推荐的精度有限。针对该问题,提出一种多重网络嵌入的图形神经网络模型来实现复杂多维社交网络下的推荐,该模型构建了统一的方法来融合用户-物品、用户-用户等各种关系构成的多维复杂网络,通过注意力机制聚合不同类型的多邻居对节点生成作出贡献,并将多个图神经网络进行组合,从而构建了多维社交关系下的图神经网络推荐框架。这种方法通过拓扑结构直接反映推荐系统中实体及其相互间关系,直接在图上对相关信息进行不断更新计算,具有很强的归纳性,有效避免了传统推荐方法中信息利用不完全的问题。通过与相关的社会推荐算法进行比较,实验结果表明,所提方法在均方根误差（RMSE）和平均绝对误差（MAE）等推荐精度指标上有所改善,甚至在数据稀疏情况下也有良好的精度。     

基于多维社交关系嵌入的深层图神经网络推荐方法

社会化推荐系统通过用户的社会属性信息能缓解推荐系统中数据稀疏性和冷启动问题，从而提高推荐系统的精度。然而大多数社会化推荐方法主要针对单一的社交网络，或对多个社交网络进行线性叠加，使得用户社会属性难以充分参与计算，因而推荐的精度有限。针对该问题，提出一种多重网络嵌入的图形神经网络模型来实现复杂多维社交网络下的推荐，该模型构建了统一的方法来融合用户-物品、用户-用户等各种关系构成的多维复杂网络，通过注意力机制聚合不同类型的多邻居对节点生成作出贡献，并将多个图神经网络进行组合，从而构建了多维社交关系下的图神经网络推荐框架。这种方法通过拓扑结构直接反映推荐系统中实体及其相互间关系，直接在图上对相关信息进行不断更新计算，具有很强的归纳性，有效避免了传统推荐方法中信息利用不完全的问题。通过与相关的社会推荐算法进行比较，实验结果表明，所提方法在均方根误差（RMSE）和平均绝对误差（MAE）等推荐精度指标上有所改善，甚至在数据稀疏情况下也有良好的精度。     

A time-aware trajectory embedding model for next-location recommendation

Next-location recommendation is an emerging task with the proliferation of location-based services. It is the task of recommending the next location to visit for a user, given her past check-in records. Although several principled solutions have been proposed for this task, existing studies have not well characterized the temporal factors in the recommendation. From three real-world datasets, our quantitative analysis reveals that temporal factors play an important role in next-location recommendation, including the periodical temporal preference and dynamic personal preference. In this paper, we propose a Time-Aware Trajectory Embedding Model (TA-TEM) to incorporate three kinds of temporal factors in next-location recommendation. Based on distributed representation learning, the proposed TA-TEM jointly models multiple kinds of temporal factors in a unified manner. TA-TEM also enhances the sequential context by using a longer context window. Experiments show that TA-TEM outperforms several competitive baselines.     

动态融合社交信息的社会化推荐

针对推荐算法中的数据稀疏问题,通常引入社交数据作为辅助信息进行社会化推荐。传统的社会化推荐算法忽略用户的兴趣迁移,导致模型无法描述用户兴趣的动态变化特征,也忽略了社交影响的动态特性,导致模型将很久以前的社交行为与近期社交行为同等对待。针对这两点提出一种社交信息动态融合的社会化推荐模型SLSRec。首先,利用自注意力机制构建用户交互物品的序列模型,以实现对用户兴趣的动态描述;然后,设计具有时间遗忘的注意力机制对社交短期兴趣进行建模,并设计具有协同特性的注意力机制对社交长期兴趣进行建模;最后,融合社交的长短期兴趣与用户的短期兴趣来获得用户的最终兴趣并产生下一项推荐。利用归一化折损累计增益（NDCG）和命中率（HR）指标在稀疏数据集brightkite和稠密数据集Last.FM上把所提模型与序列推荐模型（自注意力序列推荐（SASRec）模型）和社会化推荐模型（社会推荐的神经影响扩散（DiffNet）模型）进行对比验证。实验结果显示,SLSRec模型与DiffNet模型相比,在稀疏数据集上的HR指标提升了8.5%;与SASRec模型相比,在稠密数据集上的NDCG指标提升了2.1%,表明考虑社交信息的动态特性使推荐结果更加准确。     

A Generative Model Approach for Geo-Social Group Recommendation

With the development and prevalence of online social networks, there is an obvious tendency that people are willing to attend and share group activities with friends or acquaintances. This motivates the study on group recommendation, which aims to meet the needs of a group of users, instead of only individual users. However, how to aggregate different preferences of different group members is still a challenging problem: 1) the choice of a member in a group is influenced by various factors, e.g., personal preference, group topic, and social relationship; 2) users have different influences when in different groups. In this paper, we propose a generative geo-social group recommendation model (GSGR) to recommend points of interest (POIs) for groups. Specifically, GSGR well models the personal preference impacted by geographical information, group topics, and social influence for recommendation. Moreover, when making recommendations, GSGR aggregates the preferences of group members with different weights to estimate the preference score of a group to a POI. Experimental results on two datasets show that GSGR is effective in group recommendation and outperforms the state-of-the-art methods.     

An integrated model based on deep multimodal and rank learning for point-of-interest recommendation

Modeling point-of-Interest (POI) for recommendations is vital in location-based social networks, yet it is a challenging task due to data sparsity and cold-start problems. Most existing approaches incorporate content features into a probabilistic matrix factorization model using unsupervised learning, which results in inaccuracy and weak robustness of recommendations when data is sparse, and the cold-start problems remain unsolved. In this paper, we propose a deep multimodal rank learning (DMRL) model that improves both the accuracy and robustness of POI recommendations. DMRL exploits temporal dynamics by allowing each user to have time-dependent preferences and captures geographical influences by introducing spatial regularization to the model. DMRL jointly learns ranking for personal preferences and supervised deep learning models to create a semantic representation of POIs from multimodal content. To make model optimization converge more rapidly while preserving high effectiveness, we develop a ranking-based dynamic sampling strategy to sample adverse or negative POIs for model training. We conduct experiments to compare our DMRL model with existing models that use different approaches using two large-scale datasets obtained from Foursquare and Yelp. The experimental results demonstrate the superiority of DMRL over the other models in creating cold-start POI recommendations and achieving excellent and highly robust results for different degrees of data sparsity.

     

Personal summarization from profile networks

Personal profile information on social media like LinkedIn.com and Facebook.com is at the core of many interesting applications, such as talent recommendation and contextual advertising. However, personal profiles usually lack consistent organization confronted with the large amount of available information. Therefore, it is always a challenge for people to quickly find desired information from them. In this paper, we address the task of personal profile summarization by leveraging both textual information and social connection information in social networks from both unsupervised and supervised learning paradigms. Here, using social connection information is motivated by the intuition that people with similar academic, business or social background (e.g., comajor, co-university, and co-corporation) tend to have similar experiences and should have similar summaries. For unsupervised learning, we propose a collective ranking approach, called SocialRank, to combine textual information in an individual profile and social context information from relevant profiles in generating a personal profile summary. For supervised learning, we propose a collective factor graph model, called CoFG, to summarize personal profiles with local textual attribute functions and social connection factors. Extensive evaluation on a large dataset from LinkedIn.com demonstrates the usefulness of social connection information in personal profile summarization and the effectiveness of our proposed unsupervised and supervised learning approaches.     

A tourism destination recommender system using users’ sentiment and temporal dynamics

With the development and popularity of social networks, an increasing number of consumers prefer to order tourism products online, and like to share their experiences on social networks. Searching for tourism destinations online is a difficult task on account of its more restrictive factors. Recommender system can help these users to dispose information overload. However, such a system is affected by the issue of low recommendation accuracy and the cold-start problem. In this paper, we propose a tourism destination recommender system that employs opinion-mining technology to refine user sentiment, and make use of temporal dynamics to represent user preference and destination popularity drifting over time. These elements are then fused with the SVD+ + method by combining user sentiment and temporal influence. Compared with several well-known recommendation approaches, our method achieves improved recommendation accuracy and quality. A series of experimental evaluations, using a publicly available dataset, demonstrates that the proposed recommender system outperforms the existing recommender systems.     

融合地点影响力的兴趣点推荐算法

为解决兴趣点（POI）推荐不准确和效率低的问题,深入分析社交因素和地理位置因素的影响,提出了一种融合地点影响力的POI推荐算法。首先,为了解决签到数据稀疏的问题,将2-度好友引入协同过滤算法中构建了社交影响模型,通过计算经历和好友相似度获取2-度好友对用户的社交影响;其次,深入考虑地理位置因素对POI推荐影响,在对社交网络分析的基础上构造了地点影响力模型,通过PageRank算法发现用户影响力,结合POI被签到次数计算地点影响力,获取准确的整体位置偏好,并使用核密度估计方法对用户签到行为建模和获取个性化地理位置特征;最后,融合社交模型和地理位置模型提高推荐准确性,并通过构造POI推荐候选集来提高推荐效率。在Gowalla和Yelp签到数据集上实验,结果表明所提算法能够快速完成POI推荐,在准确率和召回率指标上明显优于融合时间因素的位置推荐（LRT）和融合地理社交因素的个性化位置推荐（iGSLR）算法。     

Context-aware trust network extraction in large-scale trust-oriented social networks

In recent years, social networking sites have been used as a means for a rich variety of activities, such as movie recommendations and product recommendations. In order to evaluate the trust between a truster (i.e., the source) and a trustee (i.e., the target) who have no direct interaction in Online Social Networks (OSNs), the trust network between them that contains important intermediate participants, the trust relations between the participants, and the social context, has an important influence on trust evaluation. Thus, to deliver a reasonable trust evaluation result, before performing any trust evaluation (i.e., trust transitivity), the contextual trust network from a given source to a given target needs to be first extracted from the social network, where constraints on social context should also be considered to guarantee the quality of the extracted networks. However, this problem has been proved to be NP-Complete. Towards solving this challenging problem, we first present a contextual trust-oriented social network structure which takes social contextual impact factors, including trust, social intimacy degree, community impact factor, preference similarity and residential location distance into account. These factors have significant influences on both social interactions between participants and trust evaluation. Then, we present a new concept QoTN (Quality of Trust Network) and propose a social context-aware trust network extraction model. Finally, we propose a Heuristic Social Context-Aware trust Network extraction algorithm (H-SCAN-K) by extending the K-Best-First Search (KBFS) method with several proposed optimization strategies. The experiments conducted on two real datasets illustrate that our proposed model and algorithm outperform the existing methods in both algorithm efficiency and the quality of the extracted trust networks.