Item Content Information Research Articles

Content-aware Recommendation via Dynamic Heterogeneous Graph Convolutional Network

With the explosive growth of products and multimedia contents on the Internet, the desire of users to find these online resources matching their interests makes it imperative to develop high quality recommendation systems. In this paper, we propose one novel neural network, namely Dynamic Heterogeneous Graph Convolutional Network (DHGCN), for item recommendation. Specifically, our proposed DHGCN consists of two components, namely the graph learner and heterogeneous graph convolution. The graph learner considers not only the user–item interactions but also user–user and item–item interactions, which are dynamically established during the graph evolution process. The heterogeneous graph convolution relies on a novel cross gating strategy to aggregate the representations yielded by the convolution over the learned heterogeneous graph and the item content information. Through comprehensive experiments on two real-world datasets, the proposed model is demonstrated to be effective on item recommendation task, outperforming the existing state-of-the-art models.

Analysis of Sentiment and Personalised Recommendation in Musical Performance.

Music performance research is a comprehensive study of aspects such as emotional analysis and personalisation in music performance, which help to add richness and creativity to the art of music performance. The labels in this paper in collaborative annotation contain rich personalised descriptive information as well as item content information and can therefore be used to help provide better recommendations. The algorithm is based on bipartite graph node structure similarity and restarted random wandering. It analyses the connection between users, items, and tags in the music social network, firstly constructs the adjacency relationship between music and tags, obtains the music recommendation list and indirectly associated music collection, then fuses the results according to the proposed algorithm, and reorders them to obtain the final recommendation list, thus realising the personalised music recommendation algorithm. The experiments show that the proposed method can meet the personalised demand of users for music on this dataset.

Tagging Items Automatically Based on Both Content Information and Browsing Behaviors

Tags have been adopted by many online services as a method to manage their online resources. Effective tagging benefits both users and firms. In real applications providing a user tagging mechanism, only a small portion of tags are usually provided by users. Therefore, an automatic tagging method, which can assign tags to different items automatically, is urgently needed. Previous works on automatic tagging focus on exploring the tagging behavior of users or the content information of items. In online service platforms, users frequently browse items related to their interests, which implies users’ judgment about the underlying features of items and is helpful for automatic tagging. Browsing-behavior records are much more plentiful compared with tagging behavior and easy to collect. However, existing studies about automatic tagging ignore this kind of information. To properly integrate both browsing behaviors and content information for automatic tagging, we propose a novel probabilistic graphical model and develop a new algorithm for the model parameter inference. We conduct thorough experiments on a real-world data set to evaluate and analyze the performance of our proposed method. The experimental results demonstrate that our approach achieves better performance than state-of-the-art automatic tagging methods. Summary of Contribution. In this paper, we study how to automatically assign tags to items in an e-commerce background. Our study is about how to perform item tagging for e-commerce and other online service providers so that consumers can easily find what they need and firms can manage their resources effectively. Specifically, we study if consumer browsing behavior can be utilized to perform the tagging task automatically, which can save efforts of both firms and consumers. Additionally, we transform the problem into how to find the most proper tags for items and propose a novel probabilistic graphical model to model the generation process of tags. Finally, we develop a variational inference algorithm to learn the model parameters, and the model shows superior performance over competing benchmark models. We believe this study contributes to machine learning techniques.

AIRC: Attentive Implicit Relation Recommendation Incorporating Content Information for Bipartite Graphs

With users being exposed to the growing volume of online information, the recommendation system aiming at mining the important or interesting information is becoming a modern research topic. One approach of recommendation is to integrate the graph neural network with deep learning algorithms. However, some of them are not tailored for bipartite graphs, which is a unique type of heterogeneous graph having two entity types. Others, though customized, neglect the importance of implicit relation and content information. In this paper, we propose the attentive implicit relation recommendation incorporating content information (AIRC) framework that is designed for bipartite graphs based on the GC–MC algorithm. First, through reconstructing the bipartite graphs, we obtain the implicit relation graphs. Then we analyze the content information of users and items with a CNN process, so that each user and item has its feature-tailored embeddings. Besides, we expand the GC–MC algorithms by adding a graph attention mechanism layer, which handles the implicit relation graph by highlighting important features and neighbors. Therefore, our framework takes into consideration both the implicit relation and content information. Finally, we test our framework on Movielens dataset and the results show that our framework performs better than other state-of-art recommendation algorithms.

Hybrid matrix factorization recommendation algorithm based on item similarity

In order to solve the problem of sparse data in matrix factorization recommendation algorithm, a hybrid matrix factorization recommendation algorithm based on item similarity is proposed. First of all, Worde2vec is used to mine the content information of items in user’s comment data to get the content similarity of items; secondly, the attribute similarity of items is calculated according to the attribute information of items; then, the content similarity and attribute similarity are fused to get the final item similarity; finally, the similarity of item is integrated into the objective function of matrix factorization algorithm. The experimental results show that the hybrid recommendation algorithm has higher accuracy, recall and coverage than the traditional matrix factorization recommendation algorithm.

A hybrid collaborative filtering recommendation algorithm: integrating content information and matrix factorisation

Matrix factorisation is a one of the most popular techniques in recommendation systems. However, matrix factorisation still suffers from cold start problem and needs complicated computation. In this paper, we present a hybrid recommendation algorithm, which integrates user and item content information and matrix factorisation. First, based on user or item content information, biases of user or item can be evaluated in advance. Incorporating user and item biases into matrix factorisation model, we can obtain final prediction model. At last, momentum stochastic gradient descent method is used to optimise other parameters. Experimental results on a real data set have shown best performance of our algorithm in terms of MAE and RMSE when compared with other classical matrix factorisation recommendation algorithms.

A hybrid collaborative filtering recommendation algorithm: integrating content information and matrix factorisation

Matrix factorisation is a one of the most popular techniques in recommendation systems. However, matrix factorisation still suffers from cold start problem and needs complicated computation. In this paper, we present a hybrid recommendation algorithm, which integrates user and item content information and matrix factorisation. First, based on user or item content information, biases of user or item can be evaluated in advance. Incorporating user and item biases into matrix factorisation model, we can obtain final prediction model. At last, momentum stochastic gradient descent method is used to optimise other parameters. Experimental results on a real data set have shown best performance of our algorithm in terms of MAE and RMSE when compared with other classical matrix factorisation recommendation algorithms.

Deep Pairwise Hashing for Cold-start Recommendation

Recommendation efficiency and data sparsity problems have been regarded as two main challenges of real-world recommendation systems. Most existing works focus on improving recommendation accuracy instead of efficiency. In this paper, we propose a Deep Pairwise Hashing (DPH) to map users and items to binary vectors in the Hamming space, where a user's preference for an item can be efficiently calculated by the Hamming distance, which significantly improves the efficiency of online recommendation. To alleviate data sparsity and cold-start problems, the item content information exploited and integrated to learn effective representations of items. Specifically, we first pre-train robust item representation from item content data by a robust Denoising Auto-encoder instead of other deterministic deep learning frameworks. Then we fine-tune the entire recommender framework by adding a pairwise loss function with discrete constraints, which is more consistent with the ultimate goal of producing a ranked list of items. Finally, we adopt the alternating optimization method to optimize the proposed model with discrete constraints. Extensive experiments conducted on three different datasets show that DPH can significantly advance the state-of-the-art frameworks regarding data sparsity and cold-start item recommendation.

Collaborative deep recommendation with global and local item correlations

Many recommendation methods have introduced item correlation information to alleviate the data sparsity and cold-start problems. However, existing approaches exploit either global or local item correlations, rarely consider both global and local item correlations, and thus they cannot provide advanced recommendation performance. Inspired by this, we propose a novel collaborative deep framework called GLICR to simultaneously incorporate the global and local item correlations into the model. More specifically, our proposed GLICR model tightly couples deep neural network with matrix factorization (MF), and jointly learns the deep feature representations of item content information in deep neural network and the rating matrix in MF. In addition, we introduce manifold regularization to learn the global and local item correlations directly from data. We conduct comprehensive experiments on real-world datasets at three different degrees of sparsity to confirm that our approach can effectively alleviate data sparsity problem and is superior to existing state-of-the-art recommendation techniques. This work is the first attempt that considers the global and local item correlations by manifold regularization in recommendation scenario.

Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms

Online interactive recommender systems strive to promptly suggest to consumers appropriate items (e.g., movies, news articles) according to the current context including both the consumer and item content information. However, such context information is often unavailable in practice for the recommendation, where only the users' interaction data on items can be utilized. Moreover, the lack of interaction records, especially for new users and items, worsens the performance of recommendation further. To address these issues, collaborative filtering (CF), one of the recommendation techniques relying on the interaction data only, as well as the online multi-armed bandit mechanisms, capable of achieving the balance between exploitation and exploration, are adopted in the online interactive recommendation settings, by assuming independent items (i.e., arms). Nonetheless, the assumption rarely holds in reality, since the real-world items tend to be correlated with each other (e.g., two articles with similar topics). In this paper, we study online interactive collaborative filtering problems by considering the dependencies among items. We explicitly formulate the item dependencies as the clusters on arms, where the arms within a single cluster share the similar latent topics. In light of the topic modeling techniques, we come up with a generative model to generate the items from their underlying topics. Furthermore, an efficient online algorithm based on particle learning is developed for inferring both latent parameters and states of our model. Additionally, our inferred model can be naturally integrated with existing multi-armed selection strategies in the online interactive collaborating setting. Empirical studies on two real-world applications, online recommendations of movies and news, demonstrate both the effectiveness and efficiency of the proposed approach.

User profile as a bridge in cross-domain recommender systems for sparsity reduction

In the past two decades, recommender systems have been successfully applied in many e-commerce companies. One of the promising techniques to generate personalized recommendations is collaborative filtering. However, it suffers from sparsity problem. Alleviating this problem, cross-domain recommender systems came into existence in which transfer learning mechanism is applied to exploit the knowledge from other related domains. While applying transfer learning, some information should overlap between source and target domains. Several attempts have been made to enhance the performance of collaborative filtering with the help of other related domains in cross-domain recommender systems framework. Although exploiting the knowledge from other domains is still challenging and open problem in recommender systems. In this paper, we propose a method namely User Profile as a Bridge in Cross-domain Recommender Systems (UP-CDRSs) for transferring knowledge between domains through user profile. Firstly, we build a user profile using demographical information of a user, explicit ratings and content information of user-rated items. Thereafter, the probabilistic graphical model is employed to learn latent factors of users and items in both domains by maximizing posterior probability. At last prediction on unrated item is estimated by an inner product of corresponding latent factors of users and items. Validating of our proposed UP-CDRSs method, we conduct series of experiments on various sparsity levels using cross-domain dataset. The results demonstrate that our proposed method substantially outperforms other without and with transfer learning methods in terms of accuracy.

Supervised Convolutional Matrix Factorization for Document Recommendation

Recently, document recommendation has become a very hot research area in online services. Since rating information is usually sparse with exploding growth of the numbers of users and items, conventional collaborative filtering-based methods degrade significantly in recommendation performance. To address this sparseness problem, auxiliary information such as item content information may be utilized. Convolution matrix factorization (ConvMF) is an appealing method, which tightly combines the rating and item content information. Although ConvMF captures contextual information of item content by utilizing convolutional neural network (CNN), the latent representation may not be effective when the rating information is very sparse. To address this problem, we generalize recent advances in supervised CNN and propose a novel recommendation model called supervised convolution matrix factorization (Super-ConvMF), which effectively combines the rating information, item content information and tag information into a unified recommendation framework. Experiments on three real-world datasets, two datasets come from MovieLens and the other one is from Amazon, show our model outperforms the state-of-the-art competitors in terms of the whole range of sparseness.

Comparison of Children's Menu Items at Full- and Quick-Service Restaurants.

The proportion of food consumed by children from restaurants tripled during the last 4 decades and that coincided with the increased rate of obesity. Despite the presence of data linking quick-service (QS) food consumption to poor diet quality, studies comparing the nutrition content of the children's menu items at QS restaurants (QSRs) with those at full-service restaurants (FSRs) are limited. The objectives of this study were to examine the nutrition content of common children's menu items at both QSRs and FSRs and compare these data with recommendations reported by the Dietary Guidelines for Americans 2015-2020, Eighth Edition. Using the 2014 data of the MenuStat project, 10 food items that are on both QSR and FSR children's menus were selected. Data from each restaurant category were aggregated and the overall average of the nutritional content of each individual food item was calculated and compared between the two restaurant categories. The average of calories, fat, carbohydrates, and added sugar of most items on the children's menu of QSRs are lower than those of FSRs. Also, most food items on children's menus of FSRs, and to a lesser extent those of QSRs, exceeded the national recommended calories and fat content per meal. Although some children's menu items of QSRs have less fat and fewer calories compared with those of FSRs, most menu items in both FSRs and QSRs do not meet national dietary recommendations. Healthcare professionals may expand discussions with patients to include both restaurant categories when counseling them and their families on obesity prevention. Also, educating children and families about reading the nutritional content information of children's menu items when eating out to make an informed choice can be a tool in fighting childhood obesity.

The formation of the information accounting system of the business entity

The article justified the urgency and benefits of developing accounting and control systems in the enterprise. Presents the author's vision of the entity and item content information accounting and control system at the level of the entity. Defines the function of the components of information accounting and control system, the implementation of which allows to form the array of analytical data necessary for the development and management decisions.

Recommendations Based on Comprehensively Exploiting the Latent Factors Hidden in Items’ Ratings and Content

To improve the performance of recommender systems in a practical manner, several hybrid approaches have been developed by considering item ratings and content information simultaneously. However, most of these hybrid approaches make recommendations based on aggregating different recommendation techniques using various strategies, rather than considering joint modeling of the item’s ratings and content, and thus fail to detect many latent factors that could potentially improve the performance of the recommender systems. For this reason, these approaches continue to suffer from data sparsity and do not work well for recommending items to individual users. A few studies try to describe a user’s preference by detecting items’ latent features from content-description texts as compensation for the sparse ratings. Unfortunately, most of these methods are still generally unable to accomplish recommendation tasks well for two reasons: (1) they learn latent factors from text descriptions or user--item ratings independently, rather than combining them together; and (2) influences of latent factors hidden in texts and ratings are not fully explored. In this study, we propose a probabilistic approach that we denote as latent random walk (LRW) based on the combination of an integrated latent topic model and random walk (RW) with the restart method, which can be used to rank items according to expected user preferences by detecting both their explicit and implicit correlative information, in order to recommend top-ranked items to potentially interested users. As presented in this article, the goal of this work is to comprehensively discover latent factors hidden in items’ ratings and content in order to alleviate the data sparsity problem and to improve the performance of recommender systems. The proposed topic model provides a generative probabilistic framework that discovers users’ implicit preferences and items’ latent features simultaneously by exploiting both ratings and item content information. On the basis of this probabilistic framework, RW can predict a user’s preference for unrated items by discovering global latent relations. In order to show the efficiency of the proposed approach, we test LRW and other state-of-the-art methods on three real-world datasets, namely, CAMRa2011, Yahoo!, and APP. The experiments indicate that our approach outperforms all comparative methods and, in addition, that it is less sensitive to the data sparsity problem, thus demonstrating the robustness of LRW for recommendation tasks.

Annotation Approach for Document with Recommendation

An enormous number of organizations generate and share textual descriptions of their products, facilities, and activities. Such collections of textual data comprise a significant amount of controlled information, which residues buried in the unstructured text. Whereas information extraction systems simplify the extraction of structured associations, they are frequently expensive and incorrect, particularly when working on top of text that does not comprise any examples of the targeted structured data. Projected an alternative methodology that simplifies the structured metadata generation by recognizing documents that are possible to contain information of awareness and this data will be beneficial for querying the database. Moreover, we intend algorithms to extract attribute-value pairs, and similarly devise new mechanisms to map such pairs to manually created schemes. We apply clustering technique to the item content information to complement the user rating information, which improves the correctness of collaborative similarity, and solves the cold start problem.

Personalized ranking with pairwise Factorization Machines

Pairwise learning is a vital technique for personalized ranking with implicit feedback. Given the assumption that each user is more interested in items which have been previously selected by the user than the remaining ones, pairwise learning algorithms can well learn users’ preference, from not only the observed user feedbacks but also the underlying interactions between users and items. However, a mass of training instances are randomly derived according to such assumption, which makes the learning procedure often converge slowly and even result in poor predictive models. In addition, the cold start problem often perplexes pairwise learning methods, since most of traditional methods in personalized ranking only take explicit ratings or implicit feedbacks into consideration. For dealing with the above issues, this work proposes a novel personalized ranking model which incorporates implicit feedback with content information by making use of Factorization Machines. For efficiently estimating the parameters of the proposed model, we develop an adaptive sampler to draw informative training instances based on content information of users and items. The experimental results show that our adaptive item sampler indeed can speed up our model, and our model outperforms advanced methods in personalized ranking.

The Association between Childhood Aerobic Fitness and Source Memory Function

Recent literature suggests that greater childhood aerobic fitness is associated with superior memory performance. Event-related brain potentials (ERPs) that have a high temporal resolution combined with behavioral task performance might further increase our understanding of the association between fitness and memory function. PURPOSE: This study was design to provide new insights into the association between childhood aerobic fitness and memory processing using ERPs during a source memory task. METHODS: Lower-fit and higher-fit children (mean = 12.0 years, SD = 1.1) performed a source memory task consisting of two test phases: an item recognition test and a source recognition test. In the former test, participants were asked to make an old/new judgement, whereas in the latter test they were asked to discriminate whether a presented line drawing was seen in a particular color (target-old) or a different color (non-target-old) from the study phase, or new. We assessed early and late ERP episodic memory (EM) effects that reflected the retrieval of item content and source information, respectively. RESULTS: Contrary to our expectation, memory accuracy was significantly lower in the higher-fit group, relative to the lower-fit group, and this difference was disproportionately greater for source recognition trials. ERP data during the source test indicated that the higher-fit group had smaller amplitude in the early EM effect, relative to the lower-fit group, whereas during the item test, the higher-fit group had a smaller amplitude in the late EM effect relative to the lower-fit group. These ERP data could reflect more flexible, but less effective retrieval processing in higher-fit children. CONCLUSIONS: It has been suggested that familiarity contributes to associative memory. Therefore, flexible retrieval processing by higher-fit children might have resulted in unexpectedly lower memory accuracy. In conclusion, it is likely that the association between childhood fitness and memory performance could be either positive, or negative, depending on the nature of the cognitive task. Supported by a NIFS (National Institute of Fitness and Sports) project (1201200005).

STCAPLRS

Newly emerging location-based social media network services (LBSMNS) provide valuable resources to understand users’ behaviors based on their location histories. The location-based behaviors of a user are generally influenced by both user intrinsic interest and the location preference, and moreover are spatial-temporal context dependent. In this article, we propose a spatial-temporal context-aware personalized location recommendation system (STCAPLRS), which offers a particular user a set of location items such as points of interest or venues (e.g., restaurants and shopping malls) within a geospatial range by considering personal interest, local preference, and spatial-temporal context influence. STCAPLRS can make accurate recommendation and facilitate people’s local visiting and new location exploration by exploiting the context information of user behavior, associations between users and location items, and the location and content information of location items. Specifically, STCAPLRS consists of two components: offline modeling and online recommendation. The core module of the offline modeling part is a context-aware regression mixture model that is designed to model the location-based user behaviors in LBSMNS to learn the interest of each individual user, the local preference of each individual location, and the context-aware influence factors. The online recommendation part takes a querying user along with the corresponding querying spatial-temporal context as input and automatically combines the learned interest of the querying user, the local preference of the querying location, and the context-aware influence factor to produce the top- k recommendations. We evaluate the performance of STCAPLRS on two real-world datasets: Dianping and Foursquare. The results demonstrate the superiority of STCAPLRS in recommending location items for users in terms of both effectiveness and efficiency. Moreover, the experimental analysis results also illustrate the excellent interpretability of STCAPLRS.

Development of an IRT-Based Short Form to Assess Applied Cognitive Function in Outpatient Rehabilitation.

Item response theory and computerized adaptive testing methods allow the development of a large calibrated item bank from which different subsets of questions can be selected for administration and scored on a common scale. The objective of this study was to develop an outpatient rehabilitation self-report short form for the Activity Measure for Post-Acute Care Applied Cognition item bank. Using data from a convenience sample of 235 rehabilitation outpatients, item content and item response theory-based test information function parameters were used in item selection. Internal consistency reliability, intraclass correlation coefficient (ICC), and percentage at the lowest (floor) and highest (ceiling) scores were evaluated for the short form and full item bank. A 15-item short form was developed. The internal consistency of the short form was 0.86. The ICC3,1 for the short form and item bank was 0.97 (95% confidence interval, 0.94-0.98). No floor effects were noted, and ceiling effects were 27.66% (short form) and 26.38% (full item bank). The Applied Cognition outpatient short form demonstrated acceptable psychometric properties and provides a bridge to item response theory-based measurement for settings where point-of-care computing is not available.