Implicit Feedback Information Research Articles

Improved negative sampling method in collaborative filtering recommendation based on Generative adversarial network

ObjectiveThe problem of low model performance caused by the lack of negative samples in the recommendation method based on implicit feedback information can be solved. MethodsThe implicit feedback recommendation model DAEGAN is constructed based on the conditional generative adversarial network framework. The Denoising Auto-Encoder is used as a generator to capture nonlinear potential factors in the interaction and improve the robustness of model. In this paper, a strong and weak negative sampling strategy is proposed, which combines the visibility of user in time points to mine uninteresting items and acquire strong negative samples, and injects these information into the model by modifying the masking mechanism to solve the problem of missing negative samples. ResultsExperiments on MovieLens 100 K, Amazon Movie and TV, MovieLens 1 M datasets show that the recommendation accuracy of CFGAN based on strong and weak negative sampling and DAEGAN proposed in this paper has been improved. LimitationsThe generation of strong negative samples is based on user interaction records, which cannot solve effectively cold start problems in extremely sparse data. ConclusionsAfter DAEGAN application, the strong and weak negative sampling method proposed in this paper has generally higher recommendation accuracy than those mainstream recommendation algorithms. The code is available at https://github.com/nanjingzhuyuxuan/DAEGAN.

Construction of a cross-domain integration teaching model for physical education oriented to the characteristics of disciplines

Abstract In this paper, we first use SemiSDAE and matrix decomposition to model the source and target domains according to the subject features and convert the encoder feature space to the matrix decomposition feature space through the feature transformation function to deeply integrate the features extracted from both. Combining the implicit feedback information of users for cross-domain recommendation and retaining the semantic information, the features of various disciplines are integrated into the online and offline cross-domain teaching based on the SPOC platform. The method in this paper has a high recall rate of 0.99 in 60% of training data, and 0.96 in 80% of training data, and the results of various sports programs are excellent, which can organically combine sports with other disciplines and promote the development and innovation of sports teaching.

FE-TCM: Filter-Enhanced Transformer Click Model for Web Search

Constructing click models and extracting implicit relevance feedback information from the interaction between users and search engines are very important to improve the ranking of search results. Using neural network to model users’ click behaviors has become one of the effective methods to construct click models. In this paper, We propose a new Filter-Enhanced Transformer Click Model (FE-TCM) for web search. The model uses Transformer as the backbone network of feature extraction and add filter layer innovatively. Firstly, in order to reduce the influence of noise on user behavior data, we use the learnable filters to filter log noise. Secondly, following the examination hypothesis, we model the attraction estimator and examination predictor respectively to output the attractiveness scores and examination probabilities. A novel transformer model is used to learn the deeper representation among different features. Finally, we apply the combination functions to integrate attractiveness scores and examination probabilities into the click prediction. From our experiments on two real-world session datasets, it is proved that FE-TCM outperforms the existing click models for the click prediction.

Fast weighted CP decomposition for context-aware recommendation with explicit and implicit feedback

As an effective method for high-dimensional information processing, tensor factorization has been widely used in context-aware recommendation. However, the multi-dimensional processing of tensor factorization usually leads to more serious data sparsity. Making full use of the data in recommendation systems, including a small amount of explicit rating data and a large amount of implicit feedback data such as clicks, plays, and purchases, can effectively alleviate this problem. Meanwhile, the processing of sparse explicit data and huge implicit feedback data makes tensor factorization face a severe challenge of computational efficiency. Therefore, this study proposes a fast tensor factorization model named FWCP that unifies explicit and implicit feedback information, which mainly studies as follows: (1) Assigning non-uniform weights to observed and unobserved values to unify explicit and implicit feedback information; (2) Memorizing intermediate data which generated by element-wise alternating least squares(ALS), and implementing parallel optimization of FWCP, which can reduce the training time of tensor factorization based on whole-data. The evaluation results on two real datasets showed that FWCP proposed in this study is superior to other context-aware recommendation algorithms.

Algorithm for generating negative cases for collaborative filtering recommender

AbstractMost collaborative filtering recommenders based on deep learning utilize implicit feedback information such as likes and bookmarks to infer user preferences rather than explicit feedback such as ratings provided by users. However, collaborative filtering models utilizing implicit feedback pose a chronic problem, that is, the “one‐class” problem (also known as the one‐class collaborative filtering problem), which causes trivial solutions due to lack of negative examples. A one‐class problem free‐boosting (OCF‐B) algorithm is proposed in this study to solve the one‐class problem by considering a user's preference pattern when generating negative cases and training the model with both positive and negative cases. More specifically, the OCF‐B algorithm iteratively selects negative cases that exacerbate the loss value of the object function and replace them with other negative cases when extracting negative cases from unknown cells of the user–item interaction matrix. In an experiment using four datasets, the results show that negative cases selected meticulously via the OCF‐B algorithm improve the prediction performance not only for negative cases, but also for positive cases. In addition, the prediction performance was better than that of the existing zero‐injection method.

A Novel Precise Personalized Learning Recommendation Model Regularized with Trust and Influence

Many precise personalized learning recommendations in massive open online courses (MOOCs) have emerged in the intelligence education field. Up to now, most researches simply put the dual learner-resources relations into consideration and are short of studies looking deep into its intrinsic social relation, thus rarely introducing the influential factors such as social trust, which means to apply the mutual trust relation between learners in the precise personalized learning recommendation. Therefore, we propose a personalized learning recommendation method based on learners’ trust and conduct a quantitative analysis on two aspects: social trust and influence, so as to realize a precise personalized learning recommendation service. First, we establish a new module on social trust scale which integrates the interactive information and preference degree to reveal the implicit trust relation between learners in social networks and construct social trust networks. Next, we adopt improved structural hole (ISH) algorithm by integrating the topological structure of social trust network with learners’ interactive information and identify the most influential learners cluster by the ISH algorithm. For the final stage, we predict the score of target learners based on explicit and implicit feedback information and realize the personalized learning recommendation for new learners. Since the score is predicted, we compare MAE and RMSE in two real-world datasets which are Canvas Network and Wanke website, respectively. The result of experiment validates the accuracy and effectiveness of our recommendation model.

A Top-N Movie Recommendation Framework Based on Deep Neural Network with Heterogeneous Modeling

To provide more accurate and stable recommendations, it is necessary to combine display information with implicit information and to dig out potential information. Existing methods only consider explicit feedback information or implicit feedback information unilaterally and ignore the potential information of explicit feedback information and implicit feedback information, which is also crucial to the accuracy of the recommendation system. However, the traditional Heterogeneous Information Networks (HIN) recommendation ignores the attribute information in the meta-path and the interaction between the user and the item and, instead, only considers the linear characteristics of the user-object often ignoring its non-linear characteristics. Aiming at the potential information acquisition problem from assorted feedback, we propose a new top-N recommendation method MFDNN for Heterogeneous Information Networks (HINs). First, we consider explicit and implicit feedback information to determine the potential preferences of users and the potential features of the product. Then, matrix factorization (MF) and a deep neural network (DNN) are fused to learn independent feature embeddings through MF and DNN, and fully considering the linear and non-linear characteristics of the user-object. MFDNN was tested on several real data sets, such as Movie-Lens, and compared with benchmark experiments. MFDNN significantly improved the hit ratio (HR) and normalized discounted cumulative gain (NDCG). Further research showed that the meta-path bias had an excellent effect on the gain of potential information mining and the fusion of explicit and implicit information in the accuracy and stability of user interest classification.

Adopting explicit and implicit social relations by SVD++ for recommendation system improvement

Recommender systems suffer a set of drawbacks such as sparsity. Social relations provide a useful source to overcome the sparsity problem. Previous studies have utilized social relations or rating feedback sources. However, they ignored integrating these sources. In this paper, the limitations of previous studies are overcome by exploiting four sources of information, namely: explicit social relationships, implicit social relationships, users’ ratings, and implicit feedback information. Firstly, implicit social relationships are extracted through the source allocation index algorithm to establish new relations among users. Secondly, the similarity method is applied to find the similarity between each pair of users who have explicit or implicit social relations. Then, users’ ratings and implicit rating feedback sources are extracted via a user-item matrix. Furthermore, all sources are integrated into the singular value decomposition plus (SVD++) method. Finally, missing predictions are computed. The proposed method is implemented on three real-world datasets: Last.Fm, FilmTrust, and Ciao. Experimental results reveal that the proposed model is superior to other studies such as SVD, SVD++, EU-SVD++, SocReg, and EISR in terms of accuracy, where the improvement of the proposed method is about 0.03% for MAE and 0.01% for RMSE when dimension value (d) = 10.

Two Models Based on Social Relations and SVD++ Method for Recommendation System

Recently, Recommender Systems (RSs) have attracted many researchers whose goal is to improve the performance of the prediction accuracy of recommendation systems by alleviating RSs drawbacks. The most common limitations are sparsity and the cold-start problem. This article proposes two models to mitigate the effects of these limitations. The proposed models exploit five sources of information: rating information, which involves two sources, namely explicit and implicit, which can be extracted via users’ ratings, and two types of social relations: explicit and implicit relations, the last source is confidence values that are included in the first model only. The whole sources are combined into the Singular Value Decomposition plus (SVD++) method. First, to extract implicit relations, each non-friend pair of users, the Multi-Steps Resource Allocation (MSRA) method is adopted to compute the probability of being friends. If the probability has accepted value which exceeds a threshold, an implicit relationship will be created. Second, the similarity of explicit and implicit social relationships for each pair of users is computed. Regarding the first model, a confidence value between each pair of users is computed by dividing the number of common items by the total number of items which have also rated by the first user of this pair. The confidence values are combined with the similarity values to produce the weight factor. Furthermore, the weight factor, explicit, and implicit feedback information are integrated into the SVD++ method to compute the missing prediction values. Additionally, three standard datasets are utilized in this study, namely Last.Fm, Ciao, and FilmTrust, to evaluate our models. The experimental results have revealed that the proposed models outperformed state-of-the-art approaches in terms of accuracy.

A hybrid recommendation model in social media based on deep emotion analysis and multi-source view fusion

The recommendation system is an effective means to solve the information overload problem that exists in social networks, which is also one of the most common applications of big data technology. Thus, the matrix decomposition recommendation model based on scoring data has been extensively studied and applied in recent years, but the data sparsity problem affects the recommendation quality of the model. To this end, this paper proposes a hybrid recommendation model based on deep emotion analysis and multi-source view fusion which makes a personalized recommendation with user-post interaction ratings, implicit feedback and auxiliary information in a hybrid recommendation system. Specifically, the HITS algorithm is used to process the data set, which can filter out the users and posts with high influence and eliminate most of the low-quality users and posts. Secondly, the calculation method of measuring the similarity of candidate posts and the method of calculating K nearest neighbors are designed, which solves the problem that the text description information of post content in the recommendation system is difficult to mine and utilize. Then, the cooperative training strategy is used to achieve the fusion of two recommended views, which eliminates the data distribution deviation added to the training data pool in the iterative training. Finally, the performance of the DMHR algorithm proposed in this paper is compared with other state-of-art algorithms based on the Twitter dataset. The experimental results show that the DMHR algorithm has significant improvements in score prediction and recommendation performance.

Leveraging contextual influence and user preferences for point-of-interest recommendation

The effective Point-of-Interest (POI) recommendation can significantly assist users to find their preferred POIs and help POI owners to attract more customers. As a result, a variety of methods have been proposed to tackle the issue of POI recommendation recently. However, it is still very difficult to precisely model the strong correlations between the POIs visited by the user and the POIs to be visited next, which leads to the poor performance of POI recommendation. In this paper, we propose a context- and preference- aware model (CPAM) to incorporate both contextual influence and user preferences into POI recommendation. Firstly, we design a Skip-Gram based POI Embedding Model (SG-PEM) to capture the contextual influence of POIs and learn the vector representation (embedding) of POIs from visiting sequences. The users’ preferences for the target POIs are obtained from the learned embeddings via similarity metric. Secondly, for the implicit feedback information contained in the check-in data, we use the Logistic Matrix Factorization (LMF) algorithm to model the users’ personalized preferences for POI. Finally, we unify SG-PEM and LMF as the CPAM model to perform personalized recommendation by leveraging contextual influence and user preferences. The experimental results on two real-world datasets of Foursquare and Gowalla show that the proposed model outperforms the state-of-the-art baselines.

Improved Metric Factorization Recommendation Algorithm Based on Social Networks and Implicit Feedback

The Metric Factorization algorithm solves the problem of the suboptimal solution caused by the inner product of the traditional matrix factorization algorithm. Although the basic metric factorization model has achieved good results in rating prediction and item ranking tasks, the algorithm ignores the role of implicit feedback and user social information. Considering the social relationship and implicit feedback information between users, this paper improves the basic metric factor Factorization algorithm, and proposes an improved metric factorization recommendation algorithm based on social networks and implicit feedback. We do rating prediction tasks on the Filmtrust and Last.FM datasets, experimental results show that the improved algorithm can further improve the accuracy of prediction.

A Hybrid Fuzzy Profiling-Nonnegative Latent Factor Model Considering Consumer Preference at Different Levels

The implicit feedback information associated with actual behavior can symmetrically reflect consumer preference, which is valuable and deserves a deep investigation. Considering the inherent uncertainty and fuzziness of implicit data, the question of how to depict consumer preference in such data is always a critical and difficult issue. In this paper, a fuzzy profiling-nonnegative latent factor (FP-NLF) model is proposed to address this problem. First, a fuzzy profiling (FP) procedure is designed for characterization of consumer preference at various levels, where the fuzzy set is introduced to manage the uncertainty and fuzziness of implicit data. Two series of strategies are provided to determine the comprehensive preference for different scenarios and commercial intentions. Subsequently, a nonnegative latent factor (NLF) model is adopted to make predictions in the case of notably sparse data. Finally, a higher quality recommendation is ultimately produced for which only the products satisfying given preference level are recommended. In addition, a case study with real data is conducted for a detailed demonstration, and the results reveal the feasibility and superiority of our proposal through comparative analysis. Finally, the sensitivity analysis explores the influences of changing weights of strategy, which can provide guidance for developing purposeful strategies to better serve consumers.

Social recommendation algorithms with user feedback information

SummarySocial media information can effectively improve the performance of personalized recommendation model. However, the feedback information in the social media which can accurately reflect users' implicit preferences is often ignored by most existing methods. To improve the users' experience and reduce the push of unwelcome information, in this article, we propose a new social recommendation algorithm with user feedback information. Different from the existing recommendation methods based on probability matrix decomposition, we incorporate the user implicit feedback information into the user rating prediction function. To reduce the data sparsity of implicit feedback information, we also adopt social network trust calculation in our algorithm. As a result, we can not only optimize the recommendation list but also filter out most of disgusting content. Compared with PMF, UserCF, CUNE, and TrustSVD, but slightly lower than RSTE, the experimental results of our model on real‐world datasets demonstrate the effectiveness of our proposed method, and further verify that the user experience is significantly improved without obviously reducing the accuracy of the recommendation.

When contextual information meets recommender systems: extended SVD++ models

ABSTRACT Collaborative filtering approach is widely used in the area of recommender systems. In fact, its predictive accuracy is supported by a large amount of additional information available on the internet, especially in social media. Singular Value Decomposition (SVD) is the most used matrix factorization method in the field of collaborative filtering, which is realized by using a latent factor vector of items and another one of users and introduces the users and item bias information. SVD++ is a derivation of the SVD model. It aims at adding implicit feedback information that is why the results of this model are improved. In this paper, different contributions are applied to SVD++ model through three different approaches which apply modification of latent factor vector while taking into account social and environmental information. Moreover, the experimental results showed that these proposed extensions ameliorate the prediction accuracy in terms of MAE and RMSE compared to SVD++ corresponding to four benchmarks, which are CiaoDVD, Food data, Adom data and Movielens-100k. According to the four used data sets, the experimental results showed that our proposed third contribution is effective in improving the prediction accuracy by 3.7%, 8.2%, 46.7% and 4%, respectively. These results also showed a reduction of the Mean Absolute Error by 0.0.71, 0.125, 0.61 and 0.038. Similar results were also obtained with the first and the second contribution.

Effective neural architectures for context-aware venue recommendation

Users in Location-Based Social Networks (LBSNs), such as Yelp and Foursquare, can search for interesting venues such as restaurants and museums to visit, or share their location with their friends by making an implicit feedback (e.g. checking in at venues they have visited). The users can also leave explicit feedback on the venues they have visited by providing ratings and/or comments. Such explicit and implicit feedback by the users provide rich information about both users and venues, and thus can be leveraged to study the users' movement in urban cities, as well as enhance the quality of personalised venue recommendations. Unlike traditional recommendation systems (e.g. book and movie recommendation systems), making effective venue recommendations is more challenging because we need to take into account the users' current context (e.g. time of the day, user's current location as well as his recently visited venues). In this thesis, based upon Matrix Factorisation (MF) and Bayesian Personalised Ranking (BPR) models, we aim to generate effective context-aware venue recommendation that a user may wish to visit based on the user's historical explicit and implicit feedbacks, the user's contextual information (e.g. the user's current location and time of the day) and additional information (e.g. the geographical location of venues and users' social relationships). To achieve this goal, we need to address the following challenges: namely (C1) modelling the users' preferences and the characteristic of venues, (C2) capturing the complex structure of user-venue interactions in a Collaborative Filtering manner, (C3) modelling the users' short-term ( dynamic ) preferences from the sequential order of user's observed feedback as well as the contextual information associated with the successive feedback, (C4) generating accurate top-K venue recommendations based on the users' preferences using a pairwise ranking-based model and (C5) appropriately sampling potential negative instances to train a ranking-based model. First, to address challenge C1 , we leverage the users' explicit feedback (e.g. their ratings and the textual content of the comments) and additional information (e.g. users' social relationships) to effectively model the users' preferences and the characteristics of venues. In particular, we propose a novel regularisation technique [1] and a factorisation-based model [2] that leverages the users' explicit feedback and the additional information to improve the rating prediction accuracy of the traditional MF model. Experiments conducted on a large scale rating dataset on LBSN demonstrate that the textual content of comments plays an important role in enhancing the accuracy of rating prediction. Second, we investigate how to leverage the users' implicit feedback and additional information such as the users' social relationship and the geographical location of venues to improve the quality of top-K venue recommendations. In particular, to address challenges C4 and C5 , we propose a novel pairwise ranking-based framework for top-K venue recommendations [3] that can incorporate multiple sources of additional information (e.g. the users' social relationship and the geographical location of venues) to effectively sample the potential negative instances. Experimental results on three large scale checkin and rating datasets from LBSNs demonstrate that the social correlations and the geographical influences play an important role to the quality of sampled negative instances and hence can improve the quality of top-K venue recommendations. Finally, to address challenges C2 and C3 , we propose a framework for sequential-based venue recommendations [4] that exploits Deep Neural Network (DNN) models to effectively capture the complex structure of user-venue interactions and the users' long-term ( dynamic ) preferences from their sequential order of checkins. Moreover, we propose a novel Recurrent Neural Network (RNN) architecture [5] that can effectively incorporate the contextual information associated with the successive implicit feedback (e.g. the time interval and the geographical distance between two successive checkins) to generate high quality context-aware venue recommendations. Experimental results on three large scale checkin and rating datasets from LBSNs demonstrate the effectiveness and robustness of our proposed framework and architecture for context-aware venue recommendations. Supervisors Dr. Craig Macdonald (University of Glasgow), Prof. Iadh Ounis (University of Glasgow) Available from : http://theses.gla.ac.uk/76735/

Deep Matrix Factorization With Implicit Feedback Embedding for Recommendation System

Automatic recommendation has become an increasingly relevant problem to industries, which allows users to discover new items that match their tastes and enables the system to target items to the right users. In this paper, we propose a deep learning (DL) based collaborative filtering framework, namely, deep matrix factorization (DMF), which can integrate any kind of side information effectively and handily. In DMF, two feature transforming functions are built to directly generate latent factors of users and items from various input information. As for the implicit feedback that is commonly used as input of recommendation algorithms, implicit feedback embedding (IFE) is proposed. IFE converts the high-dimensional and sparse implicit feedback information into a low-dimensional real-valued vector retaining primary features. Using IFE could reduce the scale of model parameters conspicuously and increase model training efficiency. Experimental results on five public databases indicate that the proposed method performs better than the state-of-the-art DL-based recommendation algorithms on both accuracy and training efficiency in terms of quantitative assessments.

A novel matrix factorization model for recommendation with LOD-based semantic similarity measure

Collaborative Filtering (CF) algorithms have been widely used to provide personalized recommendations in e-commerce websites and social network applications. Among them, Matrix Factorization (MF) is one of the most popular and efficient techniques. However, most MF-based recommender models only rely on the past transaction information of users, so there is inevitably a data sparsity problem. In this article, we propose a novel recommender model based on matrix factorization and semantic similarity measure. Firstly, we propose a new semantic similarity measure based on semantic information in the Linked Open Data (LOD) knowledge base, which is a hybrid measure based on feature and distance metrics. Then, we make an improvement on the traditional MF model to deal with data sparsity. Specifically, the MF process has been extended from both the user and item sides with implicit feedback information and semantic similar items, respectively. Experiments on two real datasets show that our proposed semantic similarity measure and recommender model are superior to the state-of-the-art approaches in recommendation performance.

Matrix Factorization for Personalized Recommendation With Implicit Feedback and Temporal Information in Social Ecommerce Networks

Collaborative filtering with implicit feedback is regarded as one of the most challenging issues in social ecommerce networks. However, the scarcity of negative feedback and the impact of time makes collaborative filtering difficult to use. Most models assign a uniform weight to missing data, but this method is invalid in the real world and leads to a biased representation of user profiles. In social ecommerce networks, the popularity of an item is implicit social information that is dynamic and can affect the preferences of a user. In this paper, we propose a smart model named TimeMF to address the above issues by incorporating implicit feedback and temporal information into social ecommerce recommendation. The weighting scheme is based on the dynamic popularity of an item. Then, we present an objective function and adopt an optimization strategy to enhance the efficiency. The experimental results for a real-world dataset reveal that our model outperforms the baselines on several metrics.

A Personalized Recommendation Algorithm Based on the User’s Implicit Feedback in E-Commerce

A recommendation system can recommend items of interest to users. However, due to the scarcity of user rating data and the similarity of single ratings, the accuracy of traditional collaborative filtering algorithms (CF) is limited. Compared with user rating data, the user’s behavior log is easier to obtain and contains a large amount of implicit feedback information, such as the purchase behavior, comparison behavior, and sequences of items (item-sequences). In this paper, we proposed a personalized recommendation algorithm based on a user’s implicit feedback (BUIF). BUIF considers not only the user’s purchase behavior but also the user’s comparison behavior and item-sequences. We extracted the purchase behavior, comparison behavior, and item-sequences from the user’s behavior log; calculated the user’s similarity by purchase behavior and comparison behavior; and extended word-embedding to item-embedding to obtain the item’s similarity. Based on the above method, we built a secondary reordering model to generate the recommendation results for users. The results of the experiment on the JData dataset show that our algorithm shows better improvement in regard to recommendation accuracy over other CF algorithms.