Recommendation List Research Articles

Effects of digital mediation and familiarity in online video interviews between peers

In times of social distancing, we need to adapt some of our research methods. Methodologies in field research can be partly replaced by a combination of online methods, which will often include online interviews. Technologically, there are few limitations to conducting interviews online, but there are side effects to digital mediation: privacy related concerns, technology hiccups, and physical distance may be barriers to disclosure for the interviewee. A survey among master students who had conducted interviews online confirmed these negative effects on the flow of interviews. Barriers to disclosure may be overcome by introducing familiarity and role-sharing. We tested the methodology of duo interviews via online video-calling tool Skype. In duo interviews, two respondents who know each other, interview each other in absence of a researcher. This explorative study investigated the effects of digital mediation on the flow of interviews and possible mitigation by familiarity between interviewer and interviewee. The qualitative study’s respondents were mostly experienced interviewers who knew each other well and were also experienced in using online video-calling tools, which reduced the influence of variation in technical and interviewing skills. The focus of the study was on finding conditions for the use of the familiarity strategy in online interviews. While familiarity between interview participants was reported to positively affect disclosure, the use of this method is limited to specific interview purposes. An unexpected finding was that the absent researcher was, in fact, present in the interview due to the element of video-recording. We list recommendations and conditions for conducting duo interviews over online video-calling tools, as well as limitations.

Collaborative filtering recommendation algorithm integrating user similarity and trust

The rapid development of the Internet has brought convenience to people and has also produced the problem of “information overload”. In view of the traditional collaborative filtering algorithm facing some bottlenecks to be solved, this study proposes a collaborative filtering algorithm that combines similarity and trust. First of all, in view of the large deviation of traditional similarity calculation and prediction of user ratings, this study proposes an optimized Pearson correlation coefficient calculation method; secondly, the trust relationship is established based on the user’s rating of the common project, and the trust relationship between users who do not have a direct trust relationship is established through the transfer of trust; then find the nearest neighbor set of the target user through the fusion of user similarity and trust; finally, the item is scored and predicted to generate a recommendation list. Experimental results show that the algorithm proposed in this study can effectively improve the accuracy of recommendation.

ACMF: An Attention Collaborative Extended Matrix Factorization Based Model for MOOC course service via a heterogeneous view

The spouting development of Massive Open Online Courses (MOOC) has enabled any learner to obtain abundant resource anytime and anywhere, offered a large-scale and open-access opportunity for learners to gain knowledge with great convenience. However, the surge of both learners and courses is engendering a sequence of issues, such as learner cognitive overload and messy course resources. The existing course resource service is not superior enough to suffice the dynamic and diverse demands of different individuals. Simultaneously, MOOC data suffers from sparsity and imbalance conundrums. To address those issues, we construct a heterogeneous information network (HIN) on MOOC to capture the plentiful heterogeneity between multiple entities and then propose an Attention Collaborative Extended Matrix Factorization Based Model, short as ACMF, for personalized recommendation service on MOOC course. In addition to learner and course subjects, we consider other four types of entities (e.g., knowledge, teacher, university, video) to give in-depth insights into why a learner is likely to enroll one course. Graph Convolutional Network with a novel node sampling algorithm based meta-path is utilized to learn the preserving structures and semantics in the MOOC HIN. Attention Mechanism is leveraged to automatically generate the final joint representation embedding. ACMF incorporates both explicit and implicit relationships via a heterogeneous view, integrates both learner and course embeddings via a specific semantic space. The ultimate personalized course recommendation list can be further adjusted based on learner-related or course-related through two tuning parameters. Experiments results on two real-world datasets collected from XuetangX and Junyi demonstrate the robustness and superiorities of ACMF.

An improved matrix factorization based model for many-objective optimization recommendation

As the application scenarios of recommendation algorithms are becoming increasingly complex, the efficiency of traditional recommendation algorithm based on accuracy is no longer satisfied. To solve this problem, an improved matrix factorization based model for many-objective optimization recommendation is proposed to simultaneously optimize the four recommendation objectives of novelty, diversity, accuracy, and recall. As a novel double-layer recommendation model, two improved algorithms are composed: 1) For the bottom layer, an improved matrix factorization algorithm with additional regularization constraints is used to predict unknown item ratings; 2) For the top layer, the recommendation list is optimized by a many-objective evolutionary algorithm. Comprehensive experiments demonstrate that the proposed model can effectively improve the four recommended evaluation metrics. And a recommended list with novel and diverse items is provided for users in a more efficient way while maintaining accuracy.

Tobacco Control Policy Simulation Models: Protocol for a Systematic Methodological Review.

BackgroundTobacco control models are mathematical models predicting tobacco-related outcomes in defined populations. The policy simulation model is considered as a subcategory of tobacco control models simulating the potential outcomes of tobacco control policy options. However, we could not identify any existing tool specifically designed to assess the quality of tobacco control models.ObjectiveThe aims of this systematic methodology review are to: (1) identify best modeling practices, (2) highlight common pitfalls, and (3) develop recommendations to assess the quality of tobacco control policy simulation models. Crucially, these recommendations can empower model users to assess the quality of current and future modeling studies, potentially leading to better tobacco policy decision-making for the public. This protocol describes the planned systematic review stages, paper inclusion and exclusion criteria, data extraction, and analysis.MethodsTwo reviewers searched five databases (Embase, EconLit, PsycINFO, PubMed, and CINAHL Plus) to identify eligible studies published between July 2013 and August 2019. We included papers projecting tobacco-related outcomes with a focus on tobacco control policies in any population and setting. Eligible papers were independently screened by two reviewers. The data extraction form was designed and piloted to extract model structure, data sources, transparency, validation, and other qualities. We will use a narrative synthesis to present the results by summarizing model trends, analyzing model approaches, and reporting data input and result quality. We will propose recommendations to assess the quality of tobacco control policy simulation models using the findings from this review and related literature.ResultsData collection is in progress. Results are expected to be completed and submitted for publication by April 2021.ConclusionsThis systematic methodological review will summarize the best practices and pitfalls existing among tobacco control policy simulation models and present a recommendation list of a high-quality tobacco control simulation model. A more standardized and quality-assured tobacco control policy simulation model will benefit modelers, policymakers, and the public on both model building and decision making.Trial RegistrationPROSPERO International Prospective Register of Systematic Reviews CRD42020178146; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42020178146International Registered Report Identifier (IRRID)DERR1-10.2196/26854

A Recommender System for Mobility-as-a-Service Plans Selection

Transportation and mobility in smart cities are undergoing a grave transformation as new ways of mobility are introduced to facilitate seamless traveling, addressing travelers’ needs in a personalized manner. A novel concept that has been recently introduced is Mobility-as-a-Service (MaaS), where mobility services are bundled in MaaS Plans and offered to end-users through a single digital platform. The present paper introduces a recommender system for MaaS Plans selection that supports travelers to select bundles of mobility services that fit their everyday transportation needs. The recommender filters out unsuitable plans and then ranks the remaining ones on the basis of their similarity to the users’ characteristics, habits and preferences. The recommendation approach is based on Constraint Satisfaction Problem (CSP) formalisms combined with cosine similarity techniques. The proposed method was evaluated in experimental settings and was further embedded in real-life pilot MaaS applications. The experimental results showed that the proposed approach provides lists of MaaS PlanMaaS Plans that users would choose in a real-life MaaS setting, in most of the cases. Moreover, the results of the real-life pilots showed that the majority of the participants chose an actual MaaS Plan from the top three places of the recommendation lists.

Top-aware recommender distillation with deep reinforcement learning

Most existing recommenders focus on providing users with a list of recommended products. In practical, users may only pay attention to the recommendations at the top positions. Our analysis, however, shows that the correctly recommended products from existing methods are not top posited; this would result in sacrificing users’ patience and engagements. To address this issue, this paper proposes a top-aware recommender distillation (TRD) framework, viz., the rank of recommendation lists from given state-of-the-art recommendation approaches are further reinforced and refined using reinforcement learning. Different from the traditional goal of knowledge distillation to mimic the behavior of its teacher, our recommender contrastingly goes step further with the goal of surpassing its teacher recommender. More importantly, our proposed TRD can be plugged on any existed recommender; thus being generic for real-world deployment. Theoretical analysis demonstrates that TRD is guaranteed to perform at least as well as the basic recommender. Extensive experiments on five state-of-the-art recommendation algorithms across three real-world datasets further show that TRD consistently improves the recommendations at top positions.

Incorporating contextual information into personalized mobile applications recommendation

With the rise of the mobile Internet, the number of mobile applications (apps) has shown explosive growth, which directly leads to the apps data overload. Currently, the recommender system has become the most effective method to solve the app data overload. However, most of the existing recommended methods for apps ignore the app functional exclusiveness features, which makes it difficult to further improve the app recommendation performance. To solve this problem, we propose a personalized context-aware mobile app recommendation approach, called PCMARA. Specifically, (1) PCMARA explores the relationship between contextual information and function of apps and constructs the app contextual factors for app which represent the function of app. (2) PCMARA leverages the app contextual factor to design a novel app similarity model, which enable to effectively eliminate the adverse effects that ignore the app functional exclusiveness. (3) PCMARA comprehensively considers the contextual information of users and apps to generate a recommendation list for users based on the target users’ current time and location. We applied the PCMARA to a real-world dataset and conducted a large-scale recommendation effect experiment. The experimental results demonstrate the superiority of PMARA over the benchmark methods.

A novel cascade hybrid many-objective recommendation algorithm incorporating multistakeholder concerns

Most previous studies of recommender systems (RSs) have particularly focused on optimizing user experience; however, users are not the only stakeholders of an RS. A pure concentration of users limits the ability to incorporate the perspectives of other stakeholders, such as providers. Furthermore, because users' preferences and providers' objectives may conflict, considering only users' views degrades the recommendation methods' utility. Therefore, we propose a cascade hybrid many-objective recommendation method (CHMAOR) to balance four objectives for two different stakeholders. CHMAOR combines provider coverage (PC), user reach coverage (URC), and provider entropy (PE) to create a new provider visibility model (PCRE). The many-objective optimization (MOP) stage includes a novel multiparent probabilistic heuristic genetic algorithm (MPPHX) that heuristically considers both parents' gene frequency and recommendation list features. Extensive experiments demonstrate the following. 1) CHMAOR effectively balances user and provider objectives in terms of accuracy, diversity, novelty, and provider visibility according to the baseline algorithms. 2) The PCRE model considers not only provider coverage but also provider appearance frequency and provider diversity while effectively changing imbalanced provider recommendations. Furthermore, PCRE dramatically reduces the complexity of high-dimensional many-objective recommendations. 3) Our MPPHX achieves better convergence and diversity solutions than the competing MOP algorithms.

A Method to Combine Multiple Recommendation Lists

A Method to Combine Multiple Recommendation Lists

Design of a recommendation system based on the transition graph

A recommendation system has been built for a web resource’s users that applies statistics about user activities to provide recommendations. The purpose of the system operation is to provide recommendations in the form of an orderly sequence of HTML pages of the resource suggested for the user. The ranking procedure uses statistical information about user transitions between web resource pages. The web resource model is represented in the form of a web graph; the user behavior model is shown as a graph of transitions between resource pages. The web graph is represented by an adjacency matrix; for the transition graph, a weighted matrix of probabilities of transitions between the vertices of the graph has been constructed. It was taken into consideration that user transitions between pages of a web resource may involve entering a URL in the address bar of a browser or by clicking on a link in the current page. The user’s transition between vertices in a finite graph according to probabilities determined by the weight of the graph’s edges is represented by a homogeneous Markov chain and is considered a process of random walk on the graph with the possibility of moving to a random vertex. Random Walk with Restarts was used to rank web resource pages for a particular user. Numerical analysis has been performed for an actual online store website. The initial data on user sessions are divided into training and test samples. According to the training sample, a weighted matrix of the probability of user transitions between web resource pages was constructed. To assess the quality of the built recommendation system, the accuracy, completeness, and Half-life Utility metrics were used. On the elements of the test sample, the accuracy value of 65‒68 % was obtained, the optimal number of elements in the recommendation list was determined. The influence of model parameters on the quality of recommendation systems was investigated.

Fair multi-stakeholder news recommender system with hypergraph ranking

Recommender systems are typically designed to fulfill end user needs. However, in some domains the users are not the only stakeholders in the system. For instance, in a news aggregator website users, authors, magazines as well as the platform itself are potential stakeholders. Most of the collaborative filtering recommender systems suffer from popularity bias. Therefore, if the recommender system only considers users’ preferences, presumably it over-represents popular providers and under-represents less popular providers. To address this issue one should consider other stakeholders in the generated ranked lists. In this paper we demonstrate that hypergraph learning has the natural capability of handling a multi-stakeholder recommendation task. A hypergraph can model high order relations between different types of objects and therefore is naturally inclined to generate recommendation lists considering multiple stakeholders. We form the recommendations in time-wise rounds and learn to adapt the weights of stakeholders to increase the coverage of low-covered stakeholders over time. The results show that the proposed approach counters popularity bias and produces fairer recommendations with respect to authors in two news datasets, at a low cost in accuracy.

Dynamic Graph Learning for Session-Based Recommendation

Session-based recommendation (SBRS) aims to make recommendations for users merely based on the ongoing session. Existing GNN-based methods achieve satisfactory performance by exploiting the pair-wise item transition pattern; however, they ignore the temporal evolution of the session graphs over different time-steps. Moreover, the widely applied cross-entropy loss with softmax in SBRS faces the serious overfitting problem. To deal with the above issues, we propose dynamic graph learning for session-based recommendation (DGL-SR). Specifically, we design a dynamic graph neural network (DGNN) to simultaneously take the graph structural information and the temporal dynamics into consideration for learning the dynamic item representations. Moreover, we propose a corrective margin softmax (CMS) to prevent overfitting in the model optimization by correcting the gradient of the negative samples. Comprehensive experiments are conducted on two benchmark datasets, that is, Diginetica and Gowalla, and the experimental results show the superiority of DGL-SR over the state-of-the-art baselines in terms of Recall@20 and MRR@20, especially on hitting the target item in the recommendation list.

A Collaborative Filtering Algorithm with Intragroup Divergence for POI Group Recommendation

The purpose of POI group recommendation is to generate a recommendation list of locations for a group of users. Most of the current studies first conduct personal recommendation and then use recommendation strategies to integrate individual recommendation results. Few studies consider the divergence of groups. To improve the precision of recommendations, we propose a POI group recommendation method based on collaborative filtering with intragroup divergence in this paper. Firstly, user preference vector is constructed based on the preference of the user on time and category. Furthermore, a computation method similar to TF-IDF is presented to compute the degree of preference of the user to the category. Secondly, we establish a group feature preference model, and the similarity of the group and other users’ feature preference is obtained based on the check-ins. Thirdly, the intragroup divergence of POIs is measured according to the POI preference of group members and their friends. Finally, the preference rating of the group for each location is calculated based on a collaborative filtering method and intragroup divergence computation, and the top-ranked score of locations are the recommendation results for the group. Experiments have been conducted on two LBSN datasets, and the experimental results on precision and recall show that the performance of the proposed method is superior to other methods.

Research on the recommendation of aerobics music adaptation based on computer aided design software

Aerobics is full of charm, and music plays an inestimable role in it. With the penetration of music in aerobics, the “sound” of music art is introduced into the “shape” of aerobics movements, and the visual art and visual experience are perfectly combined, which greatly expands the extension and extension of aerobics. This paper proposes an aerobics music adaptation recommendation algorithm that combines classification and collaborative filtering. First, by calculating the similarity of the user context information, the collaborative filtering algorithm obtains the initial annihilation grass music recommendation list; then the classification model is trained by the machine learning algorithm to obtain the user’s aerobics music type preference in a specific context; finally, collaborative filtering The obtained recommendation list is integrated with the aerobics music preference obtained by the classification model to provide personalized aerobics music adaptation recommendations for users in specific situations. In the specific aerobics music adaptation recommendation, the algorithm is implemented by a deep neural network composed of an independent cyclic neural network algorithm and an attention mechanism. In the data preprocessing stage, the audio of the user’s listening history is preprocessed by scattering transformation. The audio features of the user’s listening history are extracted by scattering transformation, and then this feature is combined with the user’s portrait to obtain a recommendation list through an independent recurrent neural network with a hybrid attention mechanism. The experimental results show that this method can effectively improve the performance of the personalized music recommendation system. Compared with the traditional single algorithm IndRNN and LSTM, the recommendation accuracy is improved by 7.8% and 20.9%, respectively.

Optimization of the Hybrid Movie Recommendation System Based on Weighted Classification and User Collaborative Filtering Algorithm

Aiming at the problem that the single model of the traditional recommendation system cannot accurately capture user preferences, this paper proposes a hybrid movie recommendation system and optimization method based on weighted classification and user collaborative filtering algorithm. The sparse linear model is used as the basic recommendation model, and the local recommendation model is trained based on user clustering, and the top-N personalized recommendation of movies is realized by fusion with the weighted classification model. According to the item category preference, the scoring matrix is converted into a low-dimensional, dense item category preference matrix, multiple cluster centers are obtained, the distance between the target user and each cluster center is calculated, and the target user is classified into the closest cluster. Finally, the collaborative filtering algorithm is used to predict the scores for the unrated items of the target user to form a recommendation list. The items are clustered through the item category preference, and the high-dimensional rating matrix is converted into a low-dimensional item category preference matrix, which further reduces the sparsity of the data. Experiments based on the Douban movie dataset verify that the recommendation algorithm proposed in this article solves the shortcomings of a single algorithm model to a certain extent and improves the recommendation effect.

Smart Campus Microservice Recommendation Algorithm Based on Neighborhood Clustering and Time Collaboration

The basic algorithm research of smart campus construction is the basic path for education to benefit from the development of science and technology. Based on the application environment of higher education teaching and management, according to the teaching periodicity and the closed-loop characteristics of the business system in universities, a neighborhood-based user attribute clustering algorithm is used in this paper to form user clusters, which are coupled micro-application clustering with periodic time. Finally, through normalized conversion and Pearson correlation coefficient analysis, the Top-N recommendation list is obtained, and a recommendation algorithm suitable for smart campus microservice system is constructed. In this paper, matrix sparsity and cold start are discussed, and data compensation is carried out by analyzing the general behavior patterns of teachers and students, which effectively solves the problem of insufficient recommendation list caused by matrix sparsity and cold start. Upon data analysis before and after the algorithm deployment, the algorithm effectively reduces the number of times that users use the search function.

DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems

With the recent prevalence of Reinforcement Learning (RL), there have been tremendous interests in utilizing RL for online advertising in recommendation platforms (e.g., e-commerce and news feed sites). However, most RL-based advertising algorithms focus on optimizing ads' revenue while ignoring the possible negative influence of ads on user experience of recommended items (products, articles and videos). Developing an optimal advertising algorithm in recommendations faces immense challenges because interpolating ads improperly or too frequently may decrease user experience, while interpolating fewer ads will reduce the advertising revenue. Thus, in this paper, we propose a novel advertising strategy for the rec/ads trade-off. To be specific, we develop an RL-based framework that can continuously update its advertising strategies and maximize reward in the long run. Given a recommendation list, we design a novel Deep Q-network architecture that can determine three internally related tasks jointly, i.e., (i) whether to interpolate an ad or not in the recommendation list, and if yes, (ii) the optimal ad and (iii) the optimal location to interpolate. The experimental results based on real-world data demonstrate the effectiveness of the proposed framework.

Towards Faster Deep Collaborative Filtering via Hierarchical Decision Networks

For personalized recommendations, collaborative filtering (CF) methods aim to recommend items to users based on data of historical user-item interactions. Deep learning has indicated success in improving performance of CF methods in recent works. However, to generate an item recommendation list for each user, a lot of deep learning based CF methods require every pair of users and items to be passed through multiple neural layers. This requires intensive computation and makes real-time end-to-end neural recommendations very costly. To address this issue, in this paper, we propose a new deep learning-based hierarchical decision network to filter out irrelevant items to save computation cost while maintaining good recommendation accuracy of deep CF methods. We also develop a distillation-based training algorithm, which uses a well-trained CF model as a teacher network to guide the training of the decision network. We conducted extensive experiments on real-world benchmark datasets to verify the effectiveness of efficiency of our decision network for making recommendations. The experimental results indicate that the proposed decision network is able to maintain or even improve the recommendation quality in terms of various metrics and meanwhile enjoy lower computational cost.

A novel POI recommendation method based on trust relationship and spatial–temporal factors

Existing point-of-interesting (POI) recommendation methods lack sufficient integration of information related to the features of individual users and their corresponding contexts. Personalized location-based services built upon these methods have a few limitations such as low recommendation accuracy and untapped potential interests of users. To overcome these limitations, we propose an efficient POI recommendation method based on multiple factors (i.e., preference, social relationship, and spatial–temporal factors) to improve the recommendation accuracy and alleviate the cold-start and sparsity problems. Unlike existing methods, the proposed method considers the features of each factor. First, we identify direct and indirect trust relationships, upon which the improved trust relationship measurement methods are built respectively. Second, we fuse the comprehensive trust relationship, user preference, check-in time, and geographical location into a matrix factorization model. We pay special attention to the attraction of items, correlation between items, trajectory composed of locations, and the influence of interest-forgetting during the fusing process. Finally, we generate recommendation lists of POIs for the target users. With three real-world datasets, experimental and analytical results show that the proposed method outperforms existing methods, while alleviating the cold-start and sparsity problems that commonly hinder POI recommender systems. Theoretically, our study contributes to the effective usage of multidimensional data science and analytics for POI recommender system design. In practice, our results can be used to improve the quality of personalized POI recommendation services for websites and applications.