Embedding Based Personalized New Paper Recommendation

More and more sensitive information of big data are being now stored in the cloud for it offers quality service and convenient management. But the Cloud Server cannot be fully trusted because it may leak information which raises security and privacy concerns of the stored data. Therefore, sensitive data has to be encrypted before shifted to the cloud. It is a great convenience for authorized users to directly retrieve the encrypted data stored in the cloud by keyword search. As we all known, returning all the matching documents is a waste of network bandwidth. Although there are some schemes that support sorting fuzzy multi-keyword search, and they are generally based on edit distance to looking for fuzzy alternatives set, which leads to significantly larger index file size and higher search complexity. Then we rank the search results according to the matching score between keywords and documents. In this paper, we give a novel multi-keyword fuzzy and sortable search scheme. We use n-gram technology to realize fuzzy search and give a novel ranking search scheme based on the fuzzy multi- keyword search. For the matching files may be more than one, there are differences between the original query keywords and the fuzzy keywords. When ranking files, we will not only consider the relevance score between the index keywords and the documents, but also the similarity between the query and keywords. Thus we calculate the comprehensive matching score of the file to the set of query keywords, which is more efficient and accurate.

In this paper, we investigate the selectivity estimation problem for streaming spatio-textual data, which arises in many social network and geo-location applications. Specifically, given a set of continuously and rapidly arriving spatio-textual objects, each of which is described by a geo-location and a short text, we aim to accurately estimate the cardinality of a spatial keyword query on objects seen so far, where a spatial keyword query consists of a search region and a set of query keywords. To the best of our knowledge, this is the first work to address this important problem. We first extend two existing techniques to solve this problem, and show their limitations. Inspired by two key observations on the "locality" of the correlations among query keywords, we propose a local correlation based method by utilizing an augmented adaptive space partition tree ( A 2 SP -tree for short) to approximately learn a local Bayesian network on-the-fly for a given query and estimate its selectivity. A novel local boosting approach is presented to further enhance the learning accuracy of local Bayesian networks. Our comprehensive experiments on real-life datasets demonstrate the superior performance of the local correlation based algorithm in terms of estimation accuracy compared to other competitors.

Classical matrix factorization approaches to collaborative filtering learn a latent vector for each user and each item, and recommendations are scored via the similarity between two such vectors, which are of the same dimension. In this work, we are motivated by the intuition that a user is a much more complicated entity than any single item, and cannot be well described by the same representation. Hence, the variety of a user's interests could be better captured by a more complex representation. We propose to model the user with a richer set of functions, specifically via a set of latent vectors, where each vector captures one of the user's latent interests or tastes. The overall recommendation model is then nonlinear where the matching score between a user and a given item is the maximum matching score over each of the user's latent interests with respect to the item's latent representation. We describe a simple, general and efficient algorithm for learning such a model, and apply it to large scale, real-world datasets from YouTube and Google Music, where our approach outperforms existing techniques.

Sequential basket analysis is a challenging task that focuses on modeling user interests through their shopping basket records. This study focuses on a newly identified bias: the repetition bias , which typically arises due to repurchase behavior . Existing methods typically oversimplify the relationship between repetitions and predictions. They assume that frequent repetition of an item by a user indicates a strong preference of the user. However, this assumption is flawed as it fails to consider that repetitions are not driven solely by user interests, as they can also be influenced by external factors, resulting in a biased understanding of user interests. In this article, we propose the CA usal intervention for R epetition D e-biasing ( CARD ), a novel solution to comprehensively estimate various influencing factors and address the repetition bias, thereby ensuring a more accurate learning of user interests. Specifically, we design a multi-factor estimation debiasing framework with constructed causal graphs to formalize the data generation process within the recommendation. We then analyze the variables that influence the recommendation, with the goal of identifying confounding variables that affect repurchase behavior and thereby locating the source of repetition bias. Since repetition bias originates from the influence of confounding variables on repurchase behavior, we resort to causal intervention methods to prevent its impacts and thus eliminate repetition bias at its source for unbiased user interest modeling. We evaluate CARD by conducting extensive experiments over three real-world datasets. The results demonstrate our approach’s competitiveness over the representative state-of-the-art baselines in achieving unbiased user interest modeling.

The proliferation of geo-textual data gives prominence to spatial keyword search. The basic top-k spatial keyword query, returns k geo-textual objects that rank the highest according to their textual relevance and spatial proximity to query keywords and a query location. We define, study, and provide means of computing the reverse top-k keyword-based location query. This new type of query takes a set of keywords, a query object q, and a number k as arguments, and it returns a spatial region such that any top-k spatial keyword query with the query keywords and a location in this region would contain object q in its result. This query targets applications in market analysis, geographical planning, and location optimization, and it may support applications related to safe zones and influence zones that are used widely in location-based services. We show that computing an exact query result requires evaluating and merging a set of weighted Voronoi cells, which is expensive. We therefore devise effective algorithms that approximate result regions with quality guarantees. We develop novel pruning techniques on top of an index, and we offer a series of optimization techniques that aim to further accelerate query processing. Empirical studies suggest that the proposed query processing is efficient and scalable.

Finding relevant information is a big challenge in today's information retrieval domain. Various applications need to find objects closest to the mentioned location that has a set of keywords. In a spatial dataset, objects are linked with some keyword(s) which specify their features. Closest Keywords is a method to query objects, using keyword cover. Algorithm based on Closest Keywords Search which exhaustively combines objects from different query keywords for generating candidate keyword covers. The increasing importance of keyword rating in object evaluation helps for the better decision making. This triggers to generate Best Keyword Cover which mainly considers inter-objects distance as well as the keyword rating of objects. When the number of query keywords gets increases, the performance of the closest keyword cover search algorithm drops significantly as a result of huge candidate keyword covers generated. To overcome this drawback, much more scalable algorithm known as keyword nearest neighbor expansion (keyword-NNE) has been proposed. Keyword-NNE algorithm significantly reduces number of candidate keyword covers generated.

Interest based selection of user generated content for rich communication services

In Recommender Systems, recommendation tasks are usually implemented by preference mining. Most existing methods in context-aware recommendation focus on learning user interests from all the records to implement preference mining. However, some records contribute to recommendations, whereas some others may reduce the performances. To address these limitations, we propose a division learning strategy to divide the original records into several groups based on regression tree techniques. Then, a two-layer preference mining process is carried out to produce group and local preferences. Finally, the two preferences are integrated by the preference integration (Prin) approach to give recommendations. The experimental results demonstrated that our model outperformed other state-of-the-art methods, which illustrated the importance of targeted modeling.

Click-through rate (CTR) prediction plays a critical role in recommender systems and other applications. Recently, modeling user behavior sequences attracts much attention and brings great improvements in the CTR field. Many existing works utilize attention mechanism or recurrent neural networks to exploit user interest from the sequence, but fail to recognize the simple truth that a user's real-time interests are inherently diverse and fluid. In this paper, we propose DisenCTR, a novel dynamic graph-based disentangled representation framework for CTR prediction. The key novelty of our method compared with existing approaches is to model evolving diverse interests of users. Specifically, we construct a time-evolving user-item interaction graph induced by historical interactions. And based on the rich dynamics supplied by the graph, we propose a disentangled graph representation module to extract diverse user interests. We further exploit the fluidity of user interests and model the temporal effect of historical behaviors using Mixture of Hawkes Process. Extensive experiments on three real-world datasets demonstrate the superior performance of our method comparing to state-of-the-art approaches.

The tremendous advance in information technology has promoted the rapid development of location-based services (LBSs), which play an indispensable role in people’s daily lives. Compared with a traditional LBS based on Point-Of-Interest (POI), which is an isolated location point, an increasing number of demands have concentrated on Region-Of-Interest (ROI) exploration, i.e., geographic regions that contain many POIs and express rich environmental information. The intention behind the POI is to search the geographical regions related to the user’s requirements, which contain some spatial objects, such as POIs and have certain environmental characteristics. In order to achieve effective ROI exploration, we propose an ROI top-k keyword query method that considers the environmental information of the regions. Specifically, the Word2Vec model has been introduced to achieve the distributed representation of POIs and capture their environmental semantics, which are then leveraged to describe the environmental characteristic information of the candidate ROI. Given a keyword query, different query patterns are designed to measure the similarities between the query keyword and the candidate ROIs to find the k candidate ROIs that are most relevant to the query. In the verification step, an evaluation criterion has been developed to test the effectiveness of the distributed representations of POIs. Finally, after generating the POI vectors in high quality, we validated the performance of the proposed ROI top-k query on a large-scale real-life dataset where the experimental results demonstrated the effectiveness of our proposals.

With the rapid development of smart TV industry, a large number of TV programs have been available for meeting various user interests, which consequently raise a great demand of building personalized TV recommender systems. Indeed, a personalized TV recommender system can greatly help users to obtain their preferred programs and assist TV and channel providers to attract more audiences. While different methods have been proposed for TV recommendations, most of them neglect the mixture of watching groups behind an individual TV. In other words, there may be different groups of audiences at different times in front of a TV. For instance, watching groups of a TV may consist of children, wife and husband, husband, wife, etc in many US household. To this end, in this paper, we propose a Mixture Probabilistic Matrix Factorization (mPMF) model to learn the program preferences of televisions, which assumes that the preference of a given television can be regarded as the mixed preference of different watching groups. Specifically, the latent vector of a television is drawn from a mixture of Gaussian and the mixture number is the estimated number of watching groups behind the television. To evaluate the proposed mPMF model, we conduct extensive experiments with many state-of-the-art baseline methods and evaluation metrics on a real-world data set. The experimental results clearly demonstrate the effectiveness of our model.

Recently, exploiting a knowledge graph (KG) to enrich the semantic representation of a news article have been proven to be effective for news recommendation. These solutions focus on the representation learning for news articles with additional information in the knowledge graph, where the user representations are mainly derived based on these news representations later. However, different users would hold different interests on the same news article. In other words, directly identifying the entities relevant to the user's interest and deriving the resultant user representation could enable a better news recommendation and explanation.

In recommender systems, one of critical tasks is to help users find their interested items among huge amount of items. The development of recommendation methods and techniques has driven many real-world recommendation applications. Desirable recommendations are vital both to the target users and the recommended items. Mining meaningful interest information from different time spans is crucial for recommendation precision. In this paper, the relations between different time spans are adopted to construct the signed networks and imitate users interest changes. First, we initially utilize temporal score information to divide different time spans. Then, the signed networks are formed at different time steps referring to users interest changes. Furthermore, considering the characteristics of signed networks, we define a new similarity measurement to grasp the common interest between two adjacent signed networks. A new adjacent matrix is obtained by weighting the network adjacent matrices of different time steps. According to the constructed dynamic evolutionary clustering model in a signed network, the nodes are divided into different clusters. Finally, the predicted ratings are calculated in each subclass instead of the entire system, which reduces the computational cost greatly. The extensive simulations are conducted based on two real-world datasets, Movielens and CiaoDVD, for demonstrating that the recommend accuracy is significantly improved using our scheme.

Cluster-of-bandit policy leverages contextual bandits in a collaborative filtering manner and aids personalized services in the online recommendation system (RecSys). When facing insufficient observations, the cluster-of-bandit policy could achieve more outstanding performance because of knowledge sharing. Cluster-of-bandit policy aims to maximize the cumulative feedback, e.g., clicks, from users. Nevertheless, in the way of their goal exist two kinds of uncertainties. First, cluster-of-bandit algorithms make recommendations according to their uncertain estimation of user interests. Second, cluster-of-bandit algorithms transfer relevant knowledge upon uncertain and noisy user clusters. Existing algorithms only consider the first one, while leaving the latter one untouched. To address the two challenges together, in this paper, we propose the ClexB policy for online RecSys. On the one hand, ClexB estimates user clustering more accurately and with less uncertainty via explorable-clustering. On the other hand, ClexB also exploits and explores user interests by sharing information within and among user clusters. In summary, ClexB explores knowledge transfer and further aids the inferences about user interests. Besides, we provide extensive empirical experiments on both the synthetic and real-world datasets and regret analysis, further consolidating the superiority of ClexB.

Users of popular services like Twitter and Facebook are often simultaneously overwhelmed with the amount of information delivered via their social connections and miss out on much content that they might have liked to see, even though it was distributed outside of their social circle. Both issues serve as difficulties to the users and drawbacks to the services.Social media service providers can benefit from understanding user interests and how they interact with the service, potentially predicting their behaviors in the future. In this paper, we address the problem of simultaneously predicting user decisions and modeling users' interests in social media by analyzing rich information gathered from Twitter. The task differs from conventional recommender systems as the cold-start problem is ubiquitous, and rich features, including textual content, need to be considered. We build predictive models for user decisions in Twitter by proposing Co-Factorization Machines (CoFM), an extension of a state-of-the-art recommendation model, to handle multiple aspects of the dataset at the same time. Additionally, we discuss and compare ranking-based loss functions in the context of recommender systems, providing the first view of how they vary from each other and perform in real tasks. We explore an extensive set of features and conduct experiments on a real-world dataset, concluding that CoFM with ranking-based loss functions is superior to state-of-the-art methods and yields interpretable latent factors.