A Deep Learning Based Approach for Context-Aware Multi-Criteria Recommender Systems

Recommender systems are similar to an information filtering system that helps identify items that best satisfy the users’ demands based on their preference profiles. Context-aware recommender systems (CARSs) and multi-criteria recommender systems (MCRSs) are extensions of traditional recommender systems. CARSs have integrated additional contextual information such as time, place, and so on for providing better recommendations. However, the majority of CARSs use ratings as a unique criterion for building communities. Meanwhile, MCRSs utilize user preferences in multiple criteria to better generate recommendations. Up to now, how to exploit context in MCRSs is still an open issue. This paper proposes a novel approach, which relies on deep learning for context-aware multi-criteria recommender systems. We apply deep neural network (DNN) models to predict the context-aware multi-criteria ratings and learn the aggregation function. We conduct experiments to evaluate the effect of this approach on the real-world dataset. A significant result is that our method outperforms other state-of-the-art methods for recommendation effectiveness.     

A user-centric evaluation of context-aware recommendations for a mobile news service

Traditional recommender systems provide personal suggestions based on the user’s preferences, without taking into account any additional contextual information, such as time or device type. The added value of contextual information for the recommendation process is highly dependent on the application domain, the type of contextual information, and variations in users’ usage behavior in different contextual situations. This paper investigates whether users utilize a mobile news service in different contextual situations and whether the context has an influence on their consumption behavior. Furthermore, the importance of context for the recommendation process is investigated by comparing the user satisfaction with recommendations based on an explicit static profile, content-based recommendations using the actual user behavior but ignoring the context, and context-aware content-based recommendations incorporating user behavior as well as context. Considering the recommendations based on the static profile as a reference condition, the results indicate a significant improvement for recommendations that are based on the actual user behavior. This improvement is due to the discrepancy between explicitly stated preferences (initial profile) and the actual consumption behavior of the user. The context-aware content-based recommendations did not significantly outperform the content-based recommendations in our user study. Context-aware content-based recommendations may induce a higher user satisfaction after a longer period of service operation, enabling the recommender to overcome the cold-start problem and distinguish user preferences in various contextual situations.     

A Graphical Model for Context-Aware Visual Content Recommendation

Existing recommender systems provide an elegant solution to the information overload in current digital libraries such as the Internet archive. Nowadays, the sensors that capture the user's contextual information such as the location and time are become available and have raised a need to personalize recommendations for each user according to his/her changing needs in different contexts. In addition, visual documents have richer textual and visual information that was not exploited by existing recommender systems. In this paper, we propose a new framework for context-aware recommendation of visual documents by modeling the user needs, the context and also the visual document collection together in a unified model. We address also the user's need for diversified recommendations. Our pilot study showed the merits of our approach in content based image retrieval.     

Non-dominated differential context modeling for context-aware recommendations

Context plays an important role in the process of decision making. A user’s preferences on the items may vary from contexts to contexts, e.g., a user may prefer to watch a different type of the movies, if he or she is going to enjoy the movie with partner rather than with children. Context-aware recommender systems, therefore, were developed to adapt the recommendations to different contextual situations, such as time, location, companion, etc. Differential context modeling is a series of recommendation models which incorporate contextual hybrid filtering into the neighborhood based collaborative filtering approaches. In this paper, we propose to enhance differential context modeling by utilizing a non-dominated user neighborhood. The notion of dominance relation was originally proposed in multi-objective optimization, and it was reused to definite non-dominated user neighborhood in collaborative filtering recently. These non-dominated user neighbors refer to the neighbors that dominate others from different perspectives of the user similarities, such as the user-user similarities based on ratings, demographic information, social relationships, and so forth. In this paper, we propose to identify the non-dominated user neighborhood by exploiting user-user similarities over multiple contextual preferences. Our experimental results can demonstrate the effectiveness of the proposed approaches in comparison with popular context-aware collaborative filtering models over five real-world contextual rating data sets.

     

Utilizing contextual ontological user profiles for personalized recommendations

As users may have different needs in different situations and contexts, it is increasingly important to consider user context data when filtering information. In the field of web personalization and recommender systems, most of the studies have focused on the process of modelling user profiles and the personalization process in order to provide personalized services to the user, but not on contextualized services. Rather limited attention has been paid to investigate how to discover, model, exploit and integrate context information in personalization systems in a generic way. In this paper, we aim at providing a novel model to build, exploit and integrate context information with a web personalization system. A context-aware personalization system (CAPS) is developed which is able to model and build contextual and personalized ontological user profiles based on the user’s interests and context information. These profiles are then exploited in order to infer and provide contextual recommendations to users. The methods and system developed are evaluated through a user study which shows that considering context information in web personalization systems can provide more effective personalization services and offer better recommendations to users.     

基于用户聚类和移动上下文的矩阵分解推荐算法研究

随着移动互联网技术的快速发展,越来越多的用户通过移动设备获取移动信息和服务,导致信息过载问题日益凸出。针对目前上下文感知推荐算法中存在的数据稀疏性差、上下文信息融入不够、用户相似性度量被忽略等问题,提出一种基于用户聚类和移动上下文的矩阵分解推荐算法。该算法通过利用k-means对用户聚类找到偏好相似的用户簇,求出每簇中并对 用户所处上下文之间的相似度并对其进行排序,由此找出与目标用户偏好和上下文均相似的用户集合,借助该集合改进传统矩阵分解模型损失函数,并以此为基准进行评分预测和推荐。仿真实验结果表明,所提算法可有效提高预测评分的准确度。     

Proposed RCFS-CARS Framework with Noise Detection and Correction

Context-Aware Recommender Systems generate more relevant recommendations by adapting them to the specific contextual situation and have become one of the most active research areas in the recommender systems. However, there remains a key issue as how contextual information can be used to create intelligent and useful recommender systems. Use of too many context variables increases dimensionality that leads to loss of accuracy while few context variables fail to bring contextual effects in recommendations. To assist the development and use of context-aware capabilities, we propose a framework, RCFS-CARS that uses influential contexts, make their sets with appropriate relaxation to be applied on different parts of the algorithm. We also propose a strategy to detect the noisy ratings in the datasets and fix them to refine the recommendation results. The experimental results on two datasets reveal that the noise detection and correction process in RCFS-CARS method is much superior and effective in context-aware recommendation scenarios.     

Context relevance assessment and exploitation in mobile recommender systems

In order to generate relevant recommendations, a context-aware recommender system (CARS) not only makes use of user preferences, but also exploits information about the specific contextual situation in which the recommended item will be consumed. For instance, when recommending a holiday destination, a CARS could take into account whether the trip will happen in summer or winter. It is unclear, however, which contextual factors are important and to which degree they influence user ratings. A large amount of data and complex context-aware predictive models must be exploited to understand these relationships. In this paper, we take a new approach for assessing and modeling the relationship between contextual factors and item ratings. Rather than using the traditional approach to data collection, where recommendations are rated with respect to real situations as participants go about their lives as normal, we simulate contextual situations to more easily capture data regarding how the context influences user ratings. To this end, we have designed a methodology whereby users are asked to judge whether a contextual factor (e.g., season) influences the rating given a certain contextual condition (e.g., season is summer). Based on the analyses of these data, we built a context-aware mobile recommender system that utilizes the contextual factors shown to be important. In a subsequent user evaluation, this system was preferred to a similar variant that did not exploit contextual information.     

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.     

Microblogs recommendations based on implicit similarity in content social networks

With the development of online social networking applications, microblogs have become a necessary online communication network in daily life. Users are interested in obtaining personalized recommendations related to their tastes and needs. In some microblog systems, tags are not available, or the use of tags is rare. In addition, user-specified social relations are extremely rare. Hence, sparsity is a problem in microblog systems. To address this problem, we propose a new framework called Pblog to alleviate sparsity. Pblog identifies users’ interests via their microblogs and social relations and computes implicit similarity among users using a new algorithm. The experimental results indicated that the use of this algorithm can improve the results. In online social networks, such as Twitter, the number of microblogs in the system is high, and it is constantly increasing. Therefore, providing personalized recommendations to target users requires considerable time. To address this problem, the Pblog framework groups similar users using the analytic hierarchy process (AHP) method. Then, Pblog prunes microblogs of the target user group and recommends microblogs with higher ratings to the target user. In the experimental results section, the Pblog framework was compared with several other frameworks. All of these frameworks were run on two datasets: Twitter and Tumblr. Based on the results of these comparisons, the Pblog framework provides more appropriate recommendations to the target user than previous frameworks.

     

Preference dynamics with multimodal user-item interactions in social media recommendation

Recommender systems elicit the interests and preferences of individuals and make recommendations accordingly, a main challenge for expert and intelligent systems. An essential problem in recommender systems is to learn users’ preference dynamics, that is, the constant evolution of the explicit or the implicit information, which is diversified throughout time according to the user actions. Also, in real settings data sparsity degrades the recommendation accuracy. Hence, state-of-the-art methods exploit multimodal information of users-item interactions to reduce sparsity, but they ignore preference dynamics and do not capture users’ most recent preferences. In this article, we present a Temporal Collective Matrix Factorization (TCMF) model, making the following contributions: (i) we capture preference dynamics through a joint decomposition model that extracts the user temporal patterns, and (ii) co-factorize the temporal patterns with multimodal user-item interactions by minimizing a joint objective function to generate the recommendations. We evaluate the performance of TCMF in terms of accuracy and root mean square error, and show that the proposed model significantly outperforms state-of-the-art strategies.     

一种上下文移动用户偏好自适应学习方法

针对移动网络对个性化移动网络服务系统的性能提出了更高的要求,但现有研究难以自适应地修改上下文移动用户偏好以为移动用户提供实时、准确的个性化移动网络服务的问题,提出了一种上下文移动用户偏好自适应学习方法,在保证精确度的基础上缩短了学习的响应时间.首先,通过分析移动用户行为日志来判断移动用户行为是否受上下文影响,并在此基础上判断移动用户行为是否发生变化.然后,根据判断结果对上下文移动用户偏好进行修正.在对发生变化的上下文移动用户偏好进行学习时,将上下文引入到最小二乘支持向量机中,进一步提出了基于上下文最小二乘支持向量机(C-LSSVM)的上下文移动用户偏好学习方法.最后,实验结果表明,当综合考虑精确度和响应时间两方面因素时,所提出的方法优于其他学习方法,并且可应用于个性化移动网络服务系统中.     

一种融合项目特征和移动用户信任关系的推荐算法

协同过滤推荐系统中普遍存在评分数据稀疏问题.传统的协同过滤推荐系统中的余弦、Pearson 等方法都是基于共同评分项目来计算用户间的相似度;而在稀疏的评分数据中,用户间共同评分的项目所占比重较小,不能准确地找到偏好相似的用户,从而影响协同过滤推荐的准确度.为了改变基于共同评分项目的用户相似度计算,使用推土机距离（earth mover's distance,简称EMD）实现跨项目的移动用户相似度计算,提出了一种融合项目特征和移动用户信任关系的协同过滤推荐算法.实验结果表明：与余弦、Pearson 方法相比,融合项目特征的用户相似度计算方法能够缓解评分数据稀疏对协同过滤算法的影响.所提出的推荐算法能够提高移动推荐的准确度.     

A Movie Recommendation System – An Application of Voting Theory in User Modeling

Our research agenda focuses on building software agents that can employ user modeling techniques to facilitate information access and management tasks. Personal assistant agents embody a clearly beneficial application of intelligent agent technology. A particular kind of assistant agents, recommender systems, can be used to recommend items of interest to users. To be successful, such systems should be able to model and reason with user preferences for items in the application domain. Our primary concern is to develop a reasoning procedure that can meaningfully and systematically tradeoff between user preferences. We have adapted mechanisms from voting theory that have desirable guarantees regarding the recommendations generated from stored preferences. To demonstrate the applicability of our technique, we have developed a movie recommender system that caters to the interests of users. We present issues and initial results based on experimental data of our research that employs voting theory for user modeling, focusing on issues that are especially important in the context of user modeling. We provide multiple query modalities by which the user can pose unconstrained, constrained, or instance-based queries. Our interactive agent learns a user model by gaining feedback aboutits recommended movies from the user. We also provide pro-active information gathering to make user interaction more rewarding. In the paper, we outline the current status of our implementation with particular emphasis on the mechanisms used to provide robust and effective recommendations.     

Improving sparsity and new user problems in collaborative filtering by clustering the personality factors

In collaborative filtering recommender systems, items recommended to an active user are selected based on the interests of users similar to him/her. Collaborative filtering systems suffer from the ‘sparsity’ and ‘new user’ problems. The former refers to the insufficiency of data about users’ preferences and the latter addresses the lack of enough information about the new-coming user. Clustering users is an effective way to improve the performance of collaborative filtering systems in facing the aforementioned problems. In previous studies, users were clustered based on characteristics such as ratings given by them as well as their age, gender, occupation, and geographical location. On the other hand, studies show that there is a significant relationship between users’ personality traits and their interests. To alleviate the sparsity and new user problems, this paper presents a new collaborative filtering system in which users are clustered based on their ‘personality traits’. In the proposed method, the personality of each user is described according to the big-5 personality model and users with similar personality are placed in the same cluster using K-means algorithm. The unknown ratings of the sparse user-item matrix are then estimated based on the clustered users, and recommendations are found for a new user according to a user-based approach which relays on the interests of the users with similar personality to him/her. In addition, for an existing user in the system, recommendations are offered in an item-based approach in which the similarity of items is estimated based on the ratings of users similar to him/her in personality. The proposed method is compared to some former collaborative filtering systems. The results demonstrate that in facing the data sparsity and new user problems, this method reduces the mean absolute error and improves the precision of the recommendations.     

A data-mining approach to preference-based data ranking founded on contextual information

The term information overload was already used back in the 1970s by Alvin Toffler in his book Future Shock, and refers to the difficulty to understand and make decisions when too much information is available. In the era of Big Data, this problem becomes much more dramatic, since users may be literally overwhelmed by the cataract of data accessible in the most varied forms. With context-aware data tailoring, given a target application, in each specific context the system allows the user to access only the view which is relevant for that application in that context. Moreover, the relative importance of information to the same user in a different context or, reciprocally, to a different user in the same context, may vary enormously; for this reason, contextual preferences can be used to further refine the views associated with contexts, by imposing a ranking on the data of each context-aware view. In this paper, we propose a methodology and a system, PREMINE (PREference MINEr), where data mining is adopted to infer contextual preferences from the past interaction of the user with contextual views over a relational database, gathering knowledge in terms of association rules between each context and the relevant data.     

Search structures and algorithms for personalized ranking

As data of an unprecedented scale are becoming accessible on the Web, personalization, of narrowing down the retrieval to meet the user-specific information needs, is becoming more and more critical. For instance, while web search engines traditionally retrieve the same results for all users, they began to offer beta services to personalize the results to adapt to user-specific contexts such as prior search history or other application contexts. In a clear contrast to search engines dealing with unstructured text data, this paper studies how to enable such personalization in the context of structured data retrieval. In particular, we adopt contextual ranking model to formalize personalization as a cost-based optimization over collected contextual rankings. With this formalism, personalization can be abstracted as a cost-optimal retrieval of contextual ranking, closely matching user-specific retrieval context. With the retrieved matching context, we adopt a machine learning approach, to effectively and efficiently identify the ideal personalized ranked results for this specific user. Our empirical evaluations over synthetic and real-life data validate both the efficiency and effectiveness of our framework.     

基于边界剪枝的不确定场境下偏好查询技术

查询执行时加入场境依赖的用户偏好可以帮助人们从大量信息中发现正确答案。已经证明,不确定场境信息条件下,用户偏好的查询可能导致NP完全或者#P完全难度的推理难题。提出了一个简单通用的方法优化不确定场境信息条件下的用户偏好查询,用户查询等价于搜索建立的场境偏好空间(contextual preferencesspace,CPS)。根据具体应用需求,考虑了两种搜索方案:搜索最优的元组和返回top-k(k为用户指定)个元组。采用定量的方法对用户偏好进行建模。为了提高查询处理效率,提出两种搜索剪枝策略:边界剪枝(branch and bound searching,BBS)和偏序边界剪枝(partial value branch and bound space searching,pBBS)。最后,从I/O访问次数和CPU运行时间两个角度评价所提出的方法。     

Modeling context-aware and intention-aware in-car infotainment systems

It is fundamental to understand users’ intentions to support them when operating a computer system with a dynamically varying set of functions, e.g., within an in-car infotainment system. The system needs to have sufficient information about its own and the user’s context to predict those intentions. Although the development of current in-car infotainment systems is already model-based, explicitly gathering and modeling contextual information and user intentions is currently not supported. However, manually creating software that understands the current context and predicts user intentions is complex, error-prone and expensive. Model-based development can help in overcoming these issues. In this paper, we present an approach for modeling a user’s intention based on Bayesian networks. We support developers of in-car infotainment systems by providing means to model possible user intentions according to the current context. We further allow modeling of user preferences and show how the modeled intentions may change during run-time as a result of the user’s behavior. We demonstrate feasibility of our approach using an industrial case study of an intention-aware in-car infotainment system. Finally, we show how modeling of contextual information and modeling user intentions can be combined by using model transformation.