English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Recommender systems are becoming more and more important in our daily lives.However, traditional recommendation methods are challenged by data sparsity andefficiency, as the numbers of users, items, and interactions between the two inmany real-world applications increase fast. In this work, we propose a novelclustering recommender system based on node2vec technology and rich informationnetwork, namely N2VSCDNNR, to solve these challenges. In particular, we use abipartite network to construct the user-item network, and represent theinteractions among users (or items) by the corresponding one-mode projectionnetwork. In order to alleviate the data sparsity problem, we enrich the networkstructure according to user and item categories, and construct the one-modeprojection category network. Then, considering the data sparsity problem in thenetwork, we employ node2vec to capture the complex latent relationships amongusers (or items) from the corresponding one-mode projection category network.Moreover, considering the dependency on parameter settings and information lossproblem in clustering methods, we use a novel spectral clustering method, whichis based on dynamic nearest-neighbors (DNN) and a novel automaticallydetermining cluster number (ADCN) method that determines the cluster centersbased on the normal distribution method, to cluster the users and itemsseparately. After clustering, we propose the two-phase personalizedrecommendation to realize the personalized recommendation of items for eachuser. A series of experiments validate the outstanding performance of ourN2VSCDNNR over several advanced embedding and side information basedrecommendation algorithms. Meanwhile, N2VSCDNNR seems to have lower timecomplexity than the baseline methods in online recommendations, indicating itspotential to be widely applied in large-scale systems.

N2VSCDNNR: A Local Recommender System Based on Node2vec and Rich Information Network