Collaborative Filtering-Based Recommendation of Online Social Voting

Yang, Xiwang; Liang, Cho–Chung; Zhao, Miao; Wang, Hongwei; Ding, Hao; Liu, Yong; Li, Yang; Zhang, Junlin

doi:10.1109/tcss.2017.2665122

Cited by 62 publications

(30 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Content-based methods [14,34] make use of user pro les or item descriptions as features for recommendation. Collaborative ltering methods [22,25,28,31] use either explicit feedback (e.g., users' ratings on items) or implicit feedback (e.g., users' browsing records about items) data of user-item interactions to nd user preference and make the recommendation. In addition, various models are incorporated into collaborative ltering, such as Support Vector Machine [30], Restricted Boltzmann Machine [24], and Stacked Denoising Auto Encoder [27].…”

Section: Related Work 21 Recommender Systemsmentioning

confidence: 99%

“…Traditional recommender systems are vulnerable to data sparsity problem and cold-start problem. To mitigate this issue, many approaches have been proposed to utilize social network information in recommender systems [3,6,10,12,25,29,31,32]. For example, [12] represents a social network as a star-structured hybrid graph centered on a social domain which connects with other item domains to help improve the prediction accuracy.…”

Section: Social Recommendationmentioning

confidence: 99%

“…Online voting [31] has recently become a popular function on social platforms, through which a user can share his opinion towards various interested subjects, ranging from livelihood issues to entertainment news. More advanced than simple like-dislike type of votings, some social networks, such as Weibo 1 , have empowered users to run their own voting campaigns.…”

Section: Introductionmentioning

confidence: 99%

“…ough several prior works [3,6,10,12,25,29,31,32] have been proposed to leverage social network information in recommendation, it is still an open question how to comprehensively incorporate structural social information into the task of voting recommendation considering its propagation pa ern. Second, users' interest in votings is strongly connected with voting content presented in question text (e.g., "Who is your favorite movie star?").…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Joint Topic-Semantic-aware Social Recommendation for Online Voting

Wang

Zhao

et al. 2017

Proceedings of the 2017 ACM on Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

Online voting is an emerging feature in social networks, in which users can express their a itudes toward various issues and show their unique interest. Online voting imposes new challenges on recommendation, because the propagation of votings heavily depends on the structure of social networks as well as the content of votings. In this paper, we investigate how to utilize these two factors in a comprehensive manner when doing voting recommendation. First, due to the fact that existing text mining methods such as topic model and semantic model cannot well process the content of votings that is typically short and ambiguous, we propose a novel Topic-Enhanced Word Embedding (TEWE) method to learn word and document representation by jointly considering their topics and semantics. en we propose our Joint Topic-Semantic-aware social Matrix Factorization (JTS-MF) model for voting recommendation. JTS-MF model calculates similarity among users and votings by combining their TEWE representation and structural information of social networks, and preserves this topic-semantic-social similarity during matrix factorization. To evaluate the performance of TEWE representation and JTS-MF model, we conduct extensive experiments on real online voting dataset. e results prove the e cacy of our approach against several state-of-the-art baselines.

show abstract

Section: Related Work 21 Recommender Systemsmentioning

confidence: 99%

Section: Social Recommendationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Joint Topic-Semantic-aware Social Recommendation for Online Voting

Wang

Zhao

et al. 2017

Proceedings of the 2017 ACM on Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…OCCF has been widely studied. This paper can also be classified into OCCF [7]. The difference is that we are dealing with binary data from multiple channels, consisting of binary user-voting activities, useruser trust relationships and user-group affiliations.…”

Section: Related Workmentioning

confidence: 99%

Discovering User Behavior and Service Score Indexing for Service Recommendation in Location Based Social Networks

2017

IJMTER

View full text Add to dashboard Cite

Abstract-The social networks are used to share information between the users. The Location Based Social Networks (LBSN) are analyzed with location and time information on check in details. The service rating prediction operations are carried out with the user location and review details. The Location Based Rating Prediction (LBRP) algorithm is applied for the service rating prediction process. The LBRP uses the three measurements for the prediction process. The user-item geographical connections, user-user geographical connections and interpersonal interest similarity measures are estimated for the rating prediction process. The user -item geographical connection indicates the distance between the user ratings and the user -item geographical locations. The user -user geographical connection indicates the user rating differences and the user -user geographical location distances. The service rating prediction process is constructed with user behavior discovery and service score index methods. The user behavior estimation process is carried out with multi activity centers. The service score estimation and index operations are performed with the attributes of the Point of Interests (POI). The user recommendation task is integrated with the system to suggest better services with reference to the user behavior and ratings. The user category, region and seasonal aspects are focused in the recommendation process.

show abstract

Job Candidate Rank Approach Using Machine Learning Techniques

Mostafa

Beshir

2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Collaborative Filtering-Based Recommendation of Online Social Voting

Cited by 62 publications

References 29 publications

Joint Topic-Semantic-aware Social Recommendation for Online Voting

Joint Topic-Semantic-aware Social Recommendation for Online Voting

Discovering User Behavior and Service Score Indexing for Service Recommendation in Location Based Social Networks

Job Candidate Rank Approach Using Machine Learning Techniques

Contact Info

Product

Resources

About