A POI-Sensitive Knowledge Graph Based Service Recommendation Method

Hu, Sihang; Tu, Zhiying; Wang, Zhongjie; Xu, Xiaofei

doi:10.1109/scc.2019.00041

Cited by 14 publications

(9 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some works such as [74,76,77], the authors bet on the reuse of linked datasets such as WordNet, DBPedia, Wikidata, Freebase, or Google Knowledge Graph. In other cases, the authors propose the creation of new KGs such as the Question-Answering KG [18], Eventcentric Tourism Knowledge Graph (ETKG) [15], POI-Sensitive Knowledge Graph [20], Cohort Knowledge Graph [75], among others. Other works perform both tasks, i.e., create a KG (DBP-FB) and reuse other existing sets to enrich or complete information on the original graph [80].…”

Section: Knowledge Graphs and Semantic Web Technologiesmentioning

confidence: 99%

“…Regarding the KG representation method (KGE), the use of a predominant method was not found. Different works highlight the use of different methods: TransE [10], TransD [68], RotatE [50], and TransH [20].…”

Section: Knowledge Graphs and Semantic Web Technologiesmentioning

confidence: 99%

“…Other works evidencing the use of multiple entities and data dimensions such as (1) Reference [68] present DCDIR, which utilizes a cross-domain mechanism to give personalized recommendations for new users in the insurance domain; (2) the KG built-in [20] incorporates data from supply-demand networks between business services and users, community network structures between users and between services, POIs, and detailed service content; (3) in [20], the KGE method called TransH is used to create dense representations of a KG; TransH facilitated the prediction of underlying relationships between users, POIs, and business services accurately.…”

Section: E-commerce Business and Financial Sectormentioning

confidence: 99%

“…On the other hand, for recommending business services, the experimental results of [20] demonstrate that the POIKG RS algorithm performs better than other collaborative filtering methods (Popularity, UserCF, ItemCF, and SPrank), especially when the data is sparse, which corresponds with a practical online scenario. Additionally, the approach can utilize the characteristics of different user groups and their POIs, resulting in better recommendation accuracy.…”

Section: E-commerce Business and Financial Sectormentioning

confidence: 99%

“…Likewise, in other areas such as tourism, RS can deliver personalized information to users, thus enhancing their tourism experience [11][12][13][14][15][16]. Other domains upon which research on knowledge graphs has been focusing are health [17,18], entertainment [19], and business [14,20].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Comprehensive Survey of Knowledge Graph-Based Recommender Systems: Technologies, Development, and Contributions

Chicaiza

Valdiviezo-Díaz

2021

Information

View full text Add to dashboard Cite

In recent years, the use of recommender systems has become popular on the web. To improve recommendation performance, usage, and scalability, the research has evolved by producing several generations of recommender systems. There is much literature about it, although most proposals focus on traditional methods’ theories and applications. Recently, knowledge graph-based recommendations have attracted attention in academia and the industry because they can alleviate information sparsity and performance problems. We found only two studies that analyze the recommendation system’s role over graphs, but they focus on specific recommendation methods. This survey attempts to cover a broader analysis from a set of selected papers. In summary, the contributions of this paper are as follows: (1) we explore traditional and more recent developments of filtering methods for a recommender system, (2) we identify and analyze proposals related to knowledge graph-based recommender systems, (3) we present the most relevant contributions using an application domain, and (4) we outline future directions of research in the domain of recommender systems. As the main survey result, we found that the use of knowledge graphs for recommendations is an efficient way to leverage and connect a user’s and an item’s knowledge, thus providing more precise results for users.

show abstract