A survey on knowledge graph-based recommender systems

Guo, Qingyu; Zhuang, Fuzhen; Qin, Chuan; Zhu, Hengshu; Xie, Xing; Xiong, Hui; He, Qing

doi:10.1360/ssi-2019-0274

Cited by 62 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1, the knowledge graph embeddings are aggregated with user/item features obtained from interaction data. Experimental results show that KGs are powerful information resources and can improve the performance of recommendation significantly (Qin et al, 2020).…”

Section: Knowledge Graph-based Recommendationmentioning

confidence: 99%

“…Therefore, by incorporating KGs into recommendation, user preference and relations between items can be captured more accurately. Many KG-based approaches are proposed recently and have achieved promising results (Zhang et al, 2016;Wang et al, 2018b;Tang et al, 2019;Qin et al, 2020). However, few works consider directly injecting external structured knowledge into pre-trained models for recommendation.…”

Section: Open Challenges and Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect

et al. 2021

View full text Add to dashboard Cite

Recommender systems aim to provide item recommendations for users and are usually faced with data sparsity problems (e.g., cold start) in real-world scenarios. Recently pre-trained models have shown their effectiveness in knowledge transfer between domains and tasks, which can potentially alleviate the data sparsity problem in recommender systems. In this survey, we first provide a review of recommender systems with pre-training. In addition, we show the benefits of pre-training to recommender systems through experiments. Finally, we discuss several promising directions for future research of recommender systems with pre-training. The source code of our experiments will be available to facilitate future research.

show abstract

Section: Knowledge Graph-based Recommendationmentioning

confidence: 99%

Section: Open Challenges and Future Directionsmentioning

confidence: 99%

Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect

et al. 2021

View full text Add to dashboard Cite

show abstract

“…We use Python 3 for the individual variation with Keras library and Tensor Flow along with Google GPUs based version for the implementation of the individual model. Furthermore, the hardware used in 12GB NVIDIA Tesla with K90 GPU, which is used up to 10 hours continually (Qin et al, 2020). The actual batch size is 600, the length of the input sequence is 235 since 260 is the maximum length of Facebook, and the input sequence is 250 since 280 is the maximum for the tweet.…”

Section: Resultsmentioning

confidence: 99%

Solicitation of Knowledge Graph Enhanced Neural Network Objects Detection by Sentiment Analysis

Conde¹

2021

ijmra

View full text Add to dashboard Cite

In the machine learning technique, the knowledge graph is advancing swiftly; however, the basic models are not able to grasp all the affluence of the script that comes from the different personal web graphics, social media, ads, and diaries, etc., ignoring the semantic of the basic text identification. The knowledge graph provides a real way to extract structured knowledge from the texts and desire images of neural network, to expedite their semantics examination. In this study, we propose a new hybrid analytic approach for sentiment evaluation based on knowledge graphs, to identify the polarity of sentiment with positive and negative attitudes in short documents, particularly in 4 chirps. We used the tweets graphs, then the similarity of graph highlighted metrics and algorithm classification pertain sentimentality pre-dictions. This technique facilitates the explicability and clarifies the results in the knowledge graph. Also, we compare our differentiate the embeddings n-gram based on sentiment analysis and the result is indicated that our study can outperform classical n-gram models, with an F1-score of 89% and recall up to 90%.

show abstract

“…They reported that these systems suffer from a cold start, lack of accuracy, and recommendation error issues. Kunaver et al 43 63 computational efficiencies, 48,50 sequence modeling 51,52 and contexts, 41,42,45,47 which suffer from the lack of efficiency of recommendation in different aspects. However, this survey comprehensively deals with IARS, including diversity, contextual features, smart sensors, edge computing-based solutions, adaptiveness, user interests, social networks, and other information resources needed for recommendations.…”

Section: Comparison With Other Existing Surveysmentioning

confidence: 99%

Developing smart city services using intent‐aware recommendation systems: A survey

Rafique

Hafid

Qadir

2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Smart cities could be defined as urban areas that use Information and Communication Technology (ICT) to solve city problems in efficient and sustainable ways. Intent-aware Recommender Systems (IARS) within ICT play a crucial role in filtering useless information according to user demands and assist in decision-making in various smart city platforms. In smart cities, the user traces on IoT, RFIDs, mobiles, and smart sensors capture actual user intent of performing an activity and enhance user satisfaction by proposing optimal services. This paper presents a detailed literature survey of the field of IARS and how it can be used for developing smart city services. First, we present the evolution of IARS with the development of computing technology. Then, we present case studies, synergies, advances, and a reference implementation architecture of IARS for smart cities. We discuss requirements for developing smart city services using IARS. Furthermore, we devise a comprehensive taxonomy of applications and techniques of IARS using different performance parameters. Finally, we elaborate on current issues, challenges, and future research directions in IARS; these directions we believe will pave the way for autonomous service provisioning in smart cities.

show abstract

A survey on knowledge graph-based recommender systems

Cited by 62 publications

References 43 publications

Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect

Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect

Solicitation of Knowledge Graph Enhanced Neural Network Objects Detection by Sentiment Analysis

Developing smart city services using intent‐aware recommendation systems: A survey

Contact Info

Product

Resources

About