2019
DOI: 10.1016/j.inffus.2018.06.004
|View full text |Cite
|
Sign up to set email alerts
|

EARS: Emotion-aware recommender system based on hybrid information fusion

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
68
0

Year Published

2020
2020
2021
2021

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 117 publications
(68 citation statements)
references
References 13 publications
0
68
0
Order By: Relevance
“…External attributes were modelled for effective software product recommendations. Quian et al [18] proposed ''EARS''(Emotion-aware recommender system based on hybrid information fusion) that uses social information, sentiment analysis and gaussian distribution based userbehaviour analysis for recommendation. Da'u and Salim [19] proposed sentiment-aware deep recommender system with neural attention network (SDRA) that uses aspect based sentiment analysis for improving recommendation accuracies.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…External attributes were modelled for effective software product recommendations. Quian et al [18] proposed ''EARS''(Emotion-aware recommender system based on hybrid information fusion) that uses social information, sentiment analysis and gaussian distribution based userbehaviour analysis for recommendation. Da'u and Salim [19] proposed sentiment-aware deep recommender system with neural attention network (SDRA) that uses aspect based sentiment analysis for improving recommendation accuracies.…”
Section: Related Workmentioning
confidence: 99%
“…Figure 16 makes it evident that recommendation precision of CISER is commendably better than conventional contentbased filtering (gain = 30%), item-based collaborative filtering (gain = 25%) and user-based collaborative filtering (gain = 24%). Figure 17 compares the proposed CISER model with previous research models, namely, CUP [20], DNN [14], TRRuSST [17] and EARS [18].CUP and DNN model user-preference trends, EARS uses emotional and socialinformation for recommendations, whereas TRRuSST quantifies product quality by manipulating external attributes modelled on user-reviews. It is clear that CISER improves recommendation efficacy with MAP@5 = 38% i.e.…”
Section: Comparison With Baseline Modelsmentioning
confidence: 99%
“…Huang et al [25] constructed a hybrid multigroup coclustering recommendation framework to cluster users and items into multiple categories simultaneously, which fully utilized various data sources including ratings and user social networks. Qian et al [26] fused three types of representative heterogeneous information to comprehensively analyze user features, such as ratings, user social networks, and user review sentiments. Zheng et al [27] considered the evolving nature of user preferences over time and developed a time-sensitive and tag-aware recommendation framework.…”
Section: Additional Data Sources For Recommender Systemsmentioning
confidence: 99%
“…The tourist attractions recommendation system has measured performance and reliability with four measurements [18] as follows:…”
Section: B Performance Evaluationmentioning
confidence: 99%