A Novel Recommendation Model Based on Trust Relations and Item Ratings in Social Networks

Song, Haokai; Pei, Qingqi; Xiao, Yang; Li, Zi; Wang, Yong

doi:10.1109/nana.2017.17

Cited by 19 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the combination method of hybrid recommendation systems, researchers have proposed seven ideas of combination: Weight, switch, mixed, feature combination, cascade, feature augmentation, and meta-level. Song et al [17] researched how to gain better recommendations of traditional recommendation models on the basis of relationship information in social networks between customers and shops and proposed a matrix decomposition framework based on integrating relationship information in social networks.…”

Section: Related Workmentioning

confidence: 99%

A Recommendation Model Based on Multi-Emotion Similarity in the Social Networks

et al. 2019

View full text Add to dashboard Cite

This paper proposed a recommendation model called RM-SA, which is based on multi-emotional analysis in networks. In the RM-MES scheme, the recommendation values of goods are primarily derived from the probabilities calculated by a similar existing recommendation system during the initiation stage of the recommendation system. First, the behaviors of those users can be divided into three aspects, including browsing goods, buying goods only, and purchasing–evaluating goods. Then, the characteristics of goods and the emotional information of user are considered to determine similarities between users and stores. We chose the most similar shop as the reference existing shop in the experiment. Then, the recommendation probability matrix of both the existing store and the new store is computed based on the similarities between users and target user, who are randomly selected. Finally, we used co-purchasing metadata from Amazon and a certain kind of comments to verify the effectiveness and performance of the RM-MES scheme proposed in this paper through comprehensive experiments. The final results showed that the precision, recall, and F1-measure were increased by 19.07%, 20.73% and 21.02% respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

A Recommendation Model Based on Multi-Emotion Similarity in the Social Networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Recently many researches have been focusing on discovering vital node as presented by Wei et al (2018), Wang et al (2017) and Kim et al (2014). Song et al (2017) proposed a recommendation model named TrustTR based on trust relations and item ratings. The model counts trusted friends' recommendations, item reputation and user history ratings in providing recommendations.…”

Section: Related Workmentioning

confidence: 99%

Strum: A Semantic Trust-Based Miner Model for Detecting Influential Spreaders in Social Networks

Wagih¹,

Mokhtar²,

Ghoniemy³

2019

Proceedings of the International Conferences Big Data Analytics, Data Mining and Computational Intelligence 2019; And Theory An

View full text Add to dashboard Cite

Social Networks have become embedded in every aspect of today people's life. The success of online social networks has a significant role in shaping trust and influence among participants. They are continuing to gain ground every day, opening the opportunity for several research movements. Great attention is now given for identifying influential spreaders in many application domains as recommendation systems, viral marketing, epidemic control and others. Most of the recent research focused only on the network structure with its geospatial information disregarding the semantics underlying these networks. In this paper, we propose a semantic trust-based miner model (STRUM) that efficiently detects influential spreaders in social networks for enhancing recommendation services. STRUM considers both geospatial information and semantic information in defining each user in the social network. Different experiments have been conducted to verify and validate the proposed algorithm against the latest published using two real location based social networks namely; Brightkite and Weeplaces are used in the experiments.

show abstract

“…Peng et al presented an evaluation model to measure both direct and indirect propagation of social influence in social networks [11]. Other approaches for improving recommendation services focus on studying the behavioral trust between nodes and its impact on the information diffusion power, as in [12,13]. Adali et al proposed a quantifiable measure of trust, which represents the communication behavior between social network participants [12].…”

Section: Introductionmentioning

confidence: 99%

“…The authors categorized behavioral trust in terms of conversational trust and propagation trust. Additionally, in [13], Song et al introduced a novel recommendation model based on trust relations and item ratings named TrustTR. The authors built their model based on trusted friends' recommendations, item reputation, and user history ratings, and experimentally proved that their model shows better accuracy compared to other prior recommendation models.…”

Section: Introductionmentioning

confidence: 99%

Exploring Trusted Relations among Virtual Interactions in Social Networks for Detecting Influence Diffusion

Wagih

Mokhtar

Ghoniemy

2019

IJGI

View full text Add to dashboard Cite

Recently, social networks have shown huge potential in terms of collaborative web services and the study of peer influence as a result of the massive amount of data, datasets, and interrelations generated. These interrelations cannot guarantee the success of online social networks without ensuring the existence of trust between nodes. Detecting influential nodes improves collaborative filtering (CF) recommendations in which nodes with the highest influential capability are most likely to be the source of recommendations. Although CF-based recommendation systems are the most widely used approach for implementing recommender systems, this approach ignores the mutual trust between users. In this paper, a trust-based algorithm (TBA) is introduced to detect influential spreaders in social networks efficiently. In particular, the proposed TBA estimates the influence that each node has on the other connected nodes as well as on the whole network. Next, a Friend-of-Friend recommendation (FoF-SocialI) algorithm is addressed to detect the influence of social ties in the recommendation process. Finally, experimental results, performed on three large scale location-based social networks, namely, Brightkite, Gowalla, and Weeplaces, to test the efficiency of the proposed algorithm, are presented. The conducted experiments show a remarkable enhancement in predicting and recommending locations in various social networks.

show abstract

A Novel Recommendation Model Based on Trust Relations and Item Ratings in Social Networks

Cited by 19 publications

References 5 publications

A Recommendation Model Based on Multi-Emotion Similarity in the Social Networks

A Recommendation Model Based on Multi-Emotion Similarity in the Social Networks

Strum: A Semantic Trust-Based Miner Model for Detecting Influential Spreaders in Social Networks

Exploring Trusted Relations among Virtual Interactions in Social Networks for Detecting Influence Diffusion

Contact Info

Product

Resources

About