Matrix Factorization Techniques for Recommender Systems

Citation recommendation describes the task of recommending citations for a given text. Due to the overload of published scientific works in recent years on the one hand, and the need to cite the most appropriate publications when writing scientific texts on the other hand, citation recommendation has emerged as an important research topic. In recent years, several approaches and evaluation data sets have been presented. However, to the best of our knowledge, no literature survey has been conducted explicitly on citation recommendation. In this article, we give a thorough introduction to automatic citation recommendation research. We then present an overview of the approaches and data sets for citation recommendation and identify differences and commonalities using various dimensions. Last but not least, we shed light on the evaluation methods and outline general challenges in the evaluation and how to meet them. We restrict ourselves to citation recommendation for scientific publications, as this document type has been studied the most in this area. However, many of the observations and discussions included in this survey are also applicable to other types of text, such as news articles and encyclopedic articles.

/pdf/citation-recommendation-approaches-and-datasets-2rvpwk5cpm.pdf

Citation recommendation: approaches and datasets

Social applications foster the involvement of end users in Web content creation, as a result of which a new source of vast amounts of data about users and their likes and dislikes has become available. Having access to users’ contributions to social sites and gaining insights into the consumers’ needs is of the utmost importance for marketing decision making in general, and to advertisement recommendation in particular. By analyzing this information, advertisement recommendation systems can attain a better understanding of the users’ interests and preferences, thus allowing these solutions to provide more precise ad suggestions. However, in addition to the already complex challenges that hamper the performance of recommender systems (i.e., data sparsity, cold-start, diversity, accuracy and scalability), new issues that should be considered have also emerged from the need to deal with heterogeneous data gathered from disparate sources. The technologies surrounding Linked Data and the Semantic Web have proved effective for knowledge management and data integration. In this work, an ontology-based advertisement recommendation system that leverages the data produced by users in social networking sites is proposed, and this approach is substantiated by a shared ontology model with which to represent both users’ profiles and the content of advertisements. Both users and advertisement are represented by means of vectors generated using natural language processing techniques, which collect ontological entities from textual content. The ad recommender framework has been extensively validated in a simulated environment, obtaining an aggregated f-measure of 79.2% and a Mean Average Precision at 3 (MAP@3) of 85.6%.

A social-semantic recommender system for advertisements

The huge amount of research papers on the web makes finding a relevant manuscript a difficult task. In recent years many models were introduced to support researchers by providing personalized citation recommendations. Moreover, deep learning methods have been employed in this domain to improve the quality of the final recommendations. However, a thorough study that classifies citation recommendation models and examines their (a) strengths and weaknesses, (b) evaluation metrics used, (c) popular datasets, and challenges faced is missing. Therefore, with this survey, we present a new classification approach for deep learning models that provide citation recommendation. Our approach uses the following six criteria: data factors, data representation methods, methodologies, types of recommendations used, problems addressed, and personalization. Additionally, we present a comparative analysis of those models that use the same set of evaluation metrics and datasets. Moreover, we examine hot upcoming issues and solutions in light of explored literature. Also, the survey discusses and analyzes the evaluation metrics and datasets adopted by the explored models. Finally, we conclude our survey with trends and future directions to further assist research on that domain.

Deep learning in citation recommendation models survey

The accelerating rate of scientific publications makes it extremely difficult for researchers to find out the relevant papers and related works. Recommender systems that aim at solving the information overload problem have attracted lots of attention. However, existing paper recommendation works generally rely on the simple citation-ships between papers, which ignore the heterogeneity of the academic graphs. In this paper, we solve the personalized paper recommendation problem in the setting of heterogeneous information networks. A heterogeneous graph representation based recommendation method named HGRec is proposed. First, the author and paper profiles are constructed based on the extracted contents information. Second, we initialize the node vectors by employing the word-embedding technique. Third, we jointly update the node embeddings in the heterogeneous graph by proposing two meta-path based proximity measures. Finally, the paper recommendation is completed by calculating the similarity of the generated author and paper feature vectors. We present experiments on a real academic network, the DBLP network. The comparative results demonstrate the effectiveness of the proposed personalized recommendation approach compared to state-of-the-art methods.

/pdf/personalized-scientific-paper-recommendation-based-on-2dy4v8t90i.pdf

Personalized Scientific Paper Recommendation Based on Heterogeneous Graph Representation

Globally, the recommendation services have become important due to the fact that they support e-commerce applications and different research communities. Recommender systems have a large number of applications in many fields, including economic, education, and scientific research. Different empirical studies have shown that the recommender systems are more effective and reliable than the keyword-based search engines for extracting useful knowledge from massive amounts of data. The problem of recommending similar scientific articles in scientific community is called scientific paper recommendation. Scientific paper recommendation aims to recommend new articles or classical articles that match researchers' interests. It has become an attractive area of study since the number of scholarly papers increases exponentially. In this paper, we first introduce the importance and advantages of the paper recommender systems. Second, we review the recommendation algorithms and methods, such as Content-based, collaborative filtering, graph-based, and hybrid methods. Then, we introduce the evaluation methods of different recommender systems. Finally, we summarize the open issues in the paper recommender systems, including cold start, sparsity, scalability, privacy, serendipity, and unified scholarly data standards. The purpose of this survey is to provide comprehensive reviews on the scholarly paper recommendation.

/pdf/scientific-paper-recommendation-a-survey-3hxnr6pptf.pdf

Scientific Paper Recommendation: A Survey

Globally, recommendation services have become important due to the fact that they support e-commerce applications and different research communities. Recommender systems have a large number of applications in many fields including economic, education, and scientific research. Different empirical studies have shown that recommender systems are more effective and reliable than keyword-based search engines for extracting useful knowledge from massive amounts of data. The problem of recommending similar scientific articles in scientific community is called scientific paper recommendation. Scientific paper recommendation aims to recommend new articles or classical articles that match researchers' interests. It has become an attractive area of study since the number of scholarly papers increases exponentially. In this survey, we first introduce the importance and advantages of paper recommender systems. Second, we review the recommendation algorithms and methods, such as Content-Based methods, Collaborative Filtering methods, Graph-Based methods and Hybrid methods. Then, we introduce the evaluation methods of different recommender systems. Finally, we summarize open issues in the paper recommender systems, including cold start, sparsity, scalability, privacy, serendipity and unified scholarly data standards. The purpose of this survey is to provide comprehensive reviews on scholarly paper recommendation.

Fairness asymmetry, changes in mutual trust, and supplier performance in buyer-supplier exchanges in China: A dyadic view

PurposeAsset specificity is a focal feature of buyer–supplier exchanges; however, whether unilateral asset specificity encourages opportunistic value expropriation or promotes trust-based value creation remains controversial. The purpose of this paper is to investigate how institutional forces shape the controversial roles of buyer asset specificity in supply chain relationships.Design/methodology/approachWith a survey of 217 matched manufacturer–supplier dyads in China, the study adopts ordinary least squares regression analyses to test hypotheses.FindingsThe results show that two key institutional forces, guanxi importance and government intervention, play different roles in shaping the value expropriation and value creation roles of buyer asset specificity. As an informal institutional force, guanxi importance weakens the impact of buyer asset specificity on opportunistic value expropriation and facilitates trust-based value creation. Moreover, as a formal institutional force, government intervention amplifies the effect of buyer asset specificity on opportunism but strengthens its connection with trust.Originality/valueBy incorporating an institutional view to investigate how institutional forces affect this “valuable but vulnerable” dilemma of asset specificity, this study reconciles the controversy concerning value expropriation vs value creation and enriches understanding of the critical roles of institutional parameters in supply chain management.

Does asset specificity lead to value expropriation or value creation? An Institutional View

Despite the long recognition of the dyadic nature of interfirm trust, prior studies have not examined how trust asymmetry affects relationship outcomes. This study examines trust asymmetry in buyer-supplier exchanges from a dyadic perspective, predicting that when buyer trust is greater than supplier trust, trust asymmetry leads to a decrease in supplier performance over time. However, when suppliers trust more than buyers, the prediction is that trust asymmetry results in an increase in supplier performance. The study further incorporates an institutional view to examine the moderating roles of legal support and regulatory uncertainty. An analysis of a two-wave survey of 229 buyer-supplier dyads provides support for the effects of trust asymmetry. Moreover, legal support weakens the negative impact of buyer trust asymmetry and the positive role of supplier trust asymmetry, while regulatory uncertainty magnifies the influence of buyer trust asymmetry. These findings provide fresh insights into the dyadic nature of trusting relationships and offer important implications for trust research and for better management of firm exchange relationships. 

Mengyang Wang

Papers

Scientific Paper Recommendation: A Survey

Scientific Paper Recommendation: A Survey

Fairness asymmetry, changes in mutual trust, and supplier performance in buyer-supplier exchanges in China: A dyadic view

Does asset specificity lead to value expropriation or value creation? An Institutional View

Trust Asymmetry and Changes in Supplier Performance: An Institutional View