Recommender System Model Research Articles

Integrating contextual sentiment analysis in collaborative recommender systems.

Recently. recommender systems have become a very crucial application in the online market and e-commerce as users are often astounded by choices and preferences and they need help finding what the best they are looking for. Recommender systems have proven to overcome information overload issues in the retrieval of information, but still suffer from persistent problems related to cold-start and data sparsity. On the flip side, sentiment analysis technique has been known in translating text and expressing user preferences. It is often used to help online businesses to observe customers' feedbacks on their products as well as try to understand customer needs and preferences. However, the current solution for embedding traditional sentiment analysis in recommender solutions seems to have limitations when involving multiple domains. Therefore, an issue called domain sensitivity should be addressed. In this paper, a sentiment-based model with contextual information for recommender system was proposed. A novel solution for domain sensitivity was proposed by applying a contextual information sentiment-based model for recommender systems. In evaluating the contributions of contextual information in sentiment-based recommendations, experiments were divided into standard rating model, standard sentiment model and contextual information model. Results showed that the proposed contextual information sentiment-based model illustrates better performance as compared to the traditional collaborative filtering approach.

A survey on trustworthy model of recommender system

A survey on trustworthy model of recommender system

Developing a mathematical model of the co-author recommender system using graph mining techniques and big data applications

Finding the most suitable co-author is one of the most important ways to conduct effective research in scientific fields. Data science has contributed to achieving this possibility significantly. The present study aims at designing a mathematical model of co-author recommender system in bioinformatics using graph mining techniques and big data applications. The present study employed an applied-developmental research method and a mixed-methods research design. The research population consisted of all scientific products in bioinformatics in the PubMed database. To achieve the research objectives, the most appropriate effective features in choosing a co-author were selected, prioritized, and weighted by experts. Then, they were weighted using graph mining techniques and big data applications. Finally, the mathematical co-author recommender system model in bioinformatics was presented. Data analysis instruments included Expert Choice, Excel, Spark, Scala and Python programming languages in a big data server. The research was conducted in four steps: (1) identifying and prioritizing the criteria effective in choosing a co-author using AHP; (2) determining the correlation degree of articles based on the criteria obtained from step 1 using algorithms and big data applications; (3) developing a mathematical co-author recommender system model; and (4) evaluating the developed mathematical model. Findings showed that the journal titles and citations criteria have the highest weight while the abstract has the lowest weight in the mathematical co-author recommender system model. The accuracy of the proposed model was 72.26. It was concluded that using content-based features and expert opinions have high potentials in recommending the most appropriate co-authors. It is expected that the proposed co-author recommender system model can provide appropriate recommendations for choosing co-authors on various fields in different contexts of scientific information. The most important innovation of this model is the use of a combination of expert opinions and systemic weights, which can accelerate the finding of co-authors and consequently saving time and achieving a greater quality of scientific products.

Differentially private locality sensitive hashing based federated recommender system

SummaryRecommender systems are important applications in big data analytics because accurate recommendation items or high‐valued suggestions can bring high profit to both commercial companies and customers. To make precise recommendations, a recommender system often needs large and fine‐grained data for training. In the current big data era, data often exists in the form of isolated islands, and it is difficult to integrate the data scattered due to privacy security concerns. Moreover, privacy laws and regulations make it harder to share data. Therefore, designing a privacy‐preserving recommender system is of paramount importance. Existing privacy‐preserving recommender system models mainly adapt cryptography approaches to achieve privacy preservation. However, cryptography approaches have heavy overhead when performing encryption and decryption operations and they lack a good level of flexibility. In this paper, we conduct privacy analysis on the existing locality sensitive hashing (LSH) approach based privacy‐preserving recommender system and show how an attacker can retrieve user's information under such a recommender system. Given such privacy risks, we propose differentially private LSH approach to build recommender system that can offer differential privacy guarantees for users. Our proposed efficient and scalable federated recommender system can make full use of multiple source data from different data owners while guaranteeing privacy preservation of users' data in contributing parties. Extensive experiments on real‐world benchmark datasets show that our approach can achieve both high time efficiency and accuracy under small privacy budgets.

DARES: An Asynchronous Distributed Recommender System Using Deep Reinforcement Learning

Traditional Recommender Systems (RS) use central servers to collect user data, compute user profiles and train global recommendation models. Central computation of RS models has great results in performance because the models are trained using all the available information and the full user profiles. However, centralised RS require users to share their whole interaction history with the central server and in general are not scalable as the number of users and interactions increases. Central RSs also have a central point of attack with respect to user privacy, because all user profiles and interactions are stored centrally. In this work we propose DARES, an distributed recommender system algorithm that uses reinforcement learning and is based on the asynchronous advantage actor-critic model (A3C). DARES is developed combining the approaches of A3C and federated learning (FL) and allows users to keep their data locally on their own devices. The system architecture consists of (i) a local recommendation model trained locally on the user devices using their interaction and (ii) a global recommendation model that is trained on a central server using the model updates that are computed on the user devices. We evaluate the proposed algorithm using well-known datasets and we compare its performance against well-known state of the art algorithms. We show that although being distributed and asynchronous, it can achieve comparable and in many cases better performance than current state-of-the-art algorithms.

Word Sequential Using Deep LSTM and Matrix Factorization to Handle Rating Sparse Data for E-Commerce Recommender System.

Recommender systems are essential engines to deliver product recommendations for e-commerce businesses. Successful adoption of recommender systems could significantly influence the growth of marketing targets. Collaborative filtering is a type of recommender system model that uses customers' activities in the past, such as ratings. Unfortunately, the number of ratings collected from customers is sparse, amounting to less than 4%. The latent factor model is a kind of collaborative filtering that involves matrix factorization to generate rating predictions. However, using only matrix factorization would result in an inaccurate recommendation. Several models include product review documents to increase the effectiveness of their rating prediction. Most of them use methods such as TF-IDF and LDA to interpret product review documents. However, traditional models such as LDA and TF-IDF face some shortcomings, in that they show a less contextual understanding of the document. This research integrated matrix factorization and novel models to interpret and understand product review documents using LSTM and word embedding. According to the experiment report, this model significantly outperformed the traditional latent factor model by more than 16% on an average and achieved 1% on an average based on RMSE evaluation metrics, compared to the previous best performance. Contextual insight of the product review document is an important aspect to improve performance in a sparse rating matrix. In the future work, generating contextual insight using bidirectional word sequential is required to increase the performance of e-commerce recommender systems with sparse data issues.

Multi-criteria tensor model for tourism recommender systems

Many tourism recommender systems have been studied to offer users the items meeting their interests. However, it is a non-trivial task to reflect the multi-criteria ratings and the cultural differences, which significantly influence users’ reviews of tourism facilities, into recommendation services. This paper proposes two “single tensor” models, consisting of users (or countries), items, multi-criteria ratings, and cultural groups, in order to consider simultaneously an inherent structure and interrelations of these factors into recommendation processes. With one Tripadvisor dataset, including 13 K users from 120 countries, experiments demonstrated that, in terms of MAE, the two proposed models for user and country give an improvement of 21.31% and 7.11% than other collaborative filtering and multi-criteria recommendation techniques. Besides, there were the positive influences of multiple-criteria ratings and cultural group factors on recommendation performances. The comparative analysis of several variants of the proposed models showed that considering Western and Eastern cultures is appropriate for improving predictive performances and their stability.

An adaptive deep learning method for item recommendation system

For many years user textual reviews have been exploited to model user/item representations for enhancing the performance of the Recommender System (RS). However, the traditional methods of the RSs basically rely on the static user/item feature vectors and ignore the fine-grained user–item interactions which could affect the accuracy of the RSs. Thus, this paper proposes a RS model that exploits neural attention techniques to learn adaptive user/item representations and fine-grained user–item interaction for enhancing the accuracy of the item recommendation. An attentive pooling layer is first designed based on the Convolutional Neural Network (CNN) to learn the adaptive latent features of the user/item from reviews. A mutual attention network technique is then introduced for modelling the fine-grained user–item​ interaction to enable jointly capturing the most informative features at the higher granularity. Finally, a prediction layer is then applied for the final prediction based on the adaptive user/item representation and the user/item importance. We extensively conduct a series of experiments using Amazon and Yelp reviews, and the results demonstrate that our proposed model performs better than the existing methods in terms of both rating prediction and ranking performances. Statistical paired test show that all the performance improvements are significant at p<0.05.

MiRTMC: A miRNA Target Prediction Method Based on Matrix Completion Algorithm.

microRNAs (miRNAs) are small non-coding RNAs which modulate the stability of gene targets and their rates of translation into proteins at transcriptional level and post-transcriptional level. miRNA dysfunctions can lead to human diseases because of dysregulation of their targets. Correct miRNA target prediction will lead to better understanding of the mechanisms of human diseases and provide hints on curing them. In recent years, computational miRNA target prediction methods have been proposed according to the interaction rules between miRNAs and targets. However, these methods suffer from high false positive rates due to the complicated relationship between miRNAs and their targets. The rapidly growing number of experimentally validated miRNA targets enables predicting miRNA targets with high precision via accurate data analysis. Taking advantage of these known miRNA targets, a novel recommendation system model (miRTMC) for miRNA target prediction is established using a new matrix completion algorithm. In miRTMC, a heterogeneous network is constructed by integrating the miRNA similarity network, the gene similarity network, and the miRNA-gene interaction network. Our assumption is that the latent factors determining whether a gene is the target of miRNA or not are highly correlated, i.e., the adjacency matrix of the heterogeneous network is low-rank, which is then completed by using a nuclear norm regularized linear least squares model under non-negative constraints. Alternating direction method of multipliers (ADMM) is adopted to numerically solve the matrix completion problem. Our results show that miRTMC outperforms the competing methods in terms of various evaluation metrics. Our software package is available at https://github.com/hjiangcsu/miRTMC.

Topical affinity in short text microblogs

Knowledge-based applications like recommender systems in social networks are powered by complex network of social discussions and user connections. Short text microblog platforms like Twitter are powerful in this aspect due to their real-time content dissemination as well as having a complex mesh of user connections. For example, users on Twitter tend to consume certain content to a greater or less extent depending on their interests over time. Quantifying this degree of content consumption in certain topics is an arduous task. This is further compounded by the amount of digital information that such platforms generate at any given time. Formulation of personalized user profiles based on user interests over time and friendship network is thus a problem. Therefore, user profiling based on their interests is important for personalized third-party content recommendations on the platform. In this paper we address this problem by presenting our solution in a two-step process:- (i) Firstly, we compute users’ Degree of Interest (DoI) towards a certain topic based on the overall users’ affinity towards that topic. (ii) Secondly, we affirm this DoI by correlating it to their friendship network. Furthermore, we describe our model for DoI computation and follow-back recommendation system by learning a low-dimensional vector representation of users and their disseminated content. This representation is used to train models for prediction of correct cluster classifications. In our experiments, we use a Twitter dataset to validate our approach by computing degrees of interest for certain test users in three diverse and generic topics. Experimental results show the effectiveness of our approach in the extraction of intra-user interests and better accuracy in follow-back recommendations with diversities in the topics.

A user-knowledge crowdsourcing task assignment model and heuristic algorithm for Expert Knowledge Recommendation Systems

Expert Knowledge Recommendation System (EKRS) is a scientific research assistant system that actively provides experts with the latest domain knowledge according to their professional knowledge background. This paper applies the crowdsourcing task assignment method, taking experts as users and recommending corresponding professional knowledge as tasks. To solve the problems of inaccurate user-knowledge matching and low assignments in EKRS, a user-knowledge task assignment model is established. To maximize the number of global task assignments, the model first applies an improved greedy assignment algorithm to convert the user-knowledge task maximum assignment problem into the maximum weight problem in bipartite graphs. Based on the matching value between a task and a user, a task is assigned to the user with a high matching value. Then, the assigned tasks are sorted with the tree decomposition technique to obtain the optimal task scheduling scheme. The heuristic depth-first search algorithm (DFS+HA) is used to update the boundaries of the heuristic function quickly, and the assignment scheme of the optimal solution can be obtained efficiently through the upper and lower bounds of the search process. Finally, the algorithm was experimentally verified with artificial data sets and the real data extracted from EKRS. The experimental results indicated that the algorithm proposed in this paper can improve the amount of user-knowledge task assignment in EKRS, find the optimal assignment scheme to maximize the number of global task assignments, and improve the search efficiency.

Evaluation Of Recommendation System On A Movie Dataset

Evaluation Of Recommendation System On A Movie Dataset

A survey of attack detection approaches in collaborative filtering recommender systems

Nowadays, due to the increasing amount of data, the use of recommender systems has increased. Therefore, the quality of the recommendations for the users of these systems is very important. One of the recommender systems models is collaborative filtering (CF) which uses the ratings given by the users to the items. But many of these ratings may be noisy or inaccurate so they reduce the quality of the recommendations. Sometimes users, using fake profiles, try to change the recommendations in their favor. Since satisfaction and trust in such systems are very important and useful, it would be better to find a way to identify these types of users. Despite numerous studies on CF recommender systems, the design of a robust recommender system is still a challenging problem. In this paper, we have analyzed the 25 previous samples of research on collaborative filtering recommender system (CFRS) for attack detection from 2009 to 2019. Most of these papers focus mainly on movie recommendations. According to these analyzes, we have categorized attack detection methods on CFRS in four categories: clustering, classifying, feature extraction and probabilistic approaches. The evaluation measures, the dataset, and attacks features used in the attack detection approaches are discussed.

Independent Game Developers and Their Expectations Towards Recommender Systems

Electronic recommender systems and digital distribution as such have transformed many industries. Digital games is one of those industries where the transformation is particularly evident, as more and more games are appearing on the market, and most of the titles are published by independent game developers. Due to electronic recommender systems developers can now self-publish their content without the mediation of third parties and additional costs for their services. This change has significantly decreased the costs of game production, distribution, and marketing, allowing more studios to engage in releasing their games on their own. However, it is unclear how the developers themselves perceive the effect of electronic recommender systems of their business models. This paper presents a qualitative study on the impact of electronic recommender systems in context of independent game development. Based on semi-structured expert interviews with active game developers who have been engaged in promoting their games through electronic recommender systems, our study provides insights on how independent game developers perceive those systems as part of their value chain and their business model. The results of the study concern to (i) independent game developers to establish, adapt, review, or improve their business model, and (ii) providers and developers of electronic recommender systems as indication of needs and requirements as well as expectations of their potential content creators.

Personalized knowledge point recommendation system based on course knowledge graph

Existing class education lacks analysis of students’ learning data, which can not reasonably evaluate students’ mastery of knowledge points and locate students’ learning path in real time, nor effectively recommend the required knowledge points for students. In order to solve the above problems, a personalized knowledge point recommendation system model (KG-PKP) combined with the knowledge graph of the course is proposed. By using accuracy, answer-time and answer-types in answer records, evaluation equations which to judge students’ mastery of knowledge points can be constructed. We can extract the knowledge points in answer records and map them into the course knowledge graph. Personalized knowledge points for students can be recommended by using the semantic hierarchical relationship and sequence of knowledge points in the knowledge graph. The comparative experiment proves the validity and interpretability of the model.

A Hybrid Knowledge-Based and Collaborative Filtering Recommender System Model for Recommending Interventions to Improve Elderly Wellbeing

A Hybrid Knowledge-Based and Collaborative Filtering Recommender System Model for Recommending Interventions to Improve Elderly Wellbeing

TSCMF: Temporal and social collective matrix factorization model for recommender systems

In real-world recommender systems, user preferences are dynamic and typically change over time. Capturing the temporal dynamics of user preferences is essential to design an efficient personalized recommender system and has recently attracted significant attention. In this paper, we consider user preferences change individually over time. Moreover, based on the intuition that social influence can affect the users’ preferences in a recommender system, we propose a Temporal and Social Collective Matrix Factorization model called TSCMF for recommendation. We jointly factorize the users’ rating information and social trust information in a collective matrix factorization framework by introducing a joint objective function. We model user dynamics into this framework by learning a transition matrix of user preferences between two successive time periods for each individual user. We present an efficient optimization algorithm based on stochastic gradient descent for solving the objective function. The experiments on a real-world dataset illustrate that the proposed model outperforms the competitive methods. Moreover, the complexity analysis demonstrates that the proposed model can be scaled up to large datasets.

A Conceptual Model for the E-Commerce Application Recommendation Framework using Exploratory Search

The users helped by the search engine for online transactions in e-commerce; nonetheless, there is still a lack of search interest from the user and online shopping intentions. To boost the user's search for product recommendations, use a search engine for the quest but not for purchasing purposes. Existing frameworks have some significant problems in the recommendation technology, such as new product problems, fewer evaluation problems, a vast amount of data, etc. Many e-commerce applications lack a better search experience like an Exploratory search system. This research work aims to create a conceptual model for recommendation systems using exploratory search, to study the behavior of users and the efficacy of exploratory search in terms of the quality of the search results produced. Several machine learning algorithms are used in this research to classify e-commerce products and evaluate the performance of these algorithms. The full-text search mechanism is used to implement an exploratory search system. The exploratory search system is evaluated by three criteria called to look up, learn and investigate. After the experiments and evaluation, it is observed that AdaBoost over decision tree performs better than the other classification algorithms implemented. The exploratory search system satisfies the three requirements that are lookup learn and investigate during the search process. Contributions to this work are to build a conceptual model for the recommendation system through the dataset of user events and finding the implementation of an exploratory search mechanism in an e-commerce application.

Rational, emotional, and attentional models for recommender systems

AbstractThis work analyses the decision‐making process underlying choice behaviour. First, neural and gaze activity were recorded experimentally from different subjects performing a choice task in a Web Interface. Second, choice models and ensembles were fitted using rational, emotional, and attentional features. The model's predictions were evaluated in terms of their accuracy and rankings were made for each user. The results show that (a) the attentional models are the best in terms of its average performance across all users, (b) each subject shows a different best model, and (c) ensembles may perform better than single choice models but an optimal building method has to be found.

A Recommender System Model Using a Neural Network Based on the Self-Product Image Congruence

This study predicts consumer preference for social clothing at work, excluding uniforms using the self-product congruence theory that also establishes a model to predict the preference for recommended products that match the consumer''s own image. A total of 490 Korean male office workers participated in this study. Participants'' self-image and the product images of 20 apparel items were measured using nine adjective semantic scales (namely elegant, stable, sincere, refined, intense, luxury, bold, conspicuous, and polite). A model was then constructed to predict the consumer preferences using a neural network with Python and TensorFlow. The resulting Predict Preference Model using Product Image (PPMPI) was trained using product image and the preference of each product. Current research confirms that product preference can be predicted by the self-image instead of by entering the product image. The prediction accuracy rate of the PPMPI was over 80%. We used 490 items of test data consisting of self-images to predict the consumer preferences for using the PPMPI. The test of the PPMPI showed that the prediction rate differed depending on product attributes. The prediction rate of work apparel with normative images was over 70% and higher than for other forms of apparel.