LGA: latent genre aware micro-video recommendation on social media

Ma, Jingwei; Li, Guang; Zhong, Mingyang; Zhao, Xin; Zhu, Lei; Li, Xue

doi:10.1007/s11042-017-4827-2

Cited by 33 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The latter includes TransE [23][24][25], TransH [26][27][28][29], and TransR/CtransR [30][31][32]. The relationships are very large and very sparse in the large-scale knowledge bases; the tensor decomposition-based methods are ineffective, so it is more appropriate to select the translationbased methods [33][34][35][36].…”

Section: Knowledge Graph Representationmentioning

confidence: 99%

Collaborative Filtering Recommendation Algorithm Based on Knowledge Graph

Zeng

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

To solve the problem that collaborative filtering algorithm only uses the user-item rating matrix and does not consider semantic information, we proposed a novel collaborative filtering recommendation algorithm based on knowledge graph. Using the knowledge graph representation learning method, this method embeds the existing semantic data into a low-dimensional vector space. It integrates the semantic information of items into the collaborative filtering recommendation by calculating the semantic similarity between items. The shortcoming of collaborative filtering algorithm which does not consider the semantic information of items is overcome, and therefore the effect of collaborative filtering recommendation is improved on the semantic level. Experimental results show that the proposed algorithm can get higher values on precision, recall, and F-measure for collaborative filtering recommendation.

show abstract

Section: Knowledge Graph Representationmentioning

confidence: 99%

Collaborative Filtering Recommendation Algorithm Based on Knowledge Graph

Zeng

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The di®erence lies in the architecture of the networks, composed of aggregates of regularly spaced circuit clones (called cells), communicating with each other through their nearest neighbors. 41 Ma et al 28 employed neural networks, user characteristics, keywords and keyframes for video recommendations.…”

Section: State Of the Artmentioning

confidence: 99%

A Video Recommendation System for Complex Topic Learning Based on a Sustainable Design Approach

Meza

Yamanaka

2019

Vietnam J. Comp. Sci.

View full text Add to dashboard Cite

There are several issues compromising the educational role of social networks, particularly in the case of video-based online content. Among them, individual (cognitive and emotional), social (privacy and ethics) and structural (algorithmic bias) challenges can be found. To cope with such issues, we propose a recommendation system for online video content, applying the principles of sustainable design. Precision and recall in English were slightly lower for the system in comparison to YouTube, but the variety of recommended items increased; while in Spanish, precision and recall were higher. Expected results include fostering the adoption of complex thinking by taking on account a user’s objective and subjective contexts.

show abstract

“…(15)) for group learning and hierarchy modeling. In this experiment, α is varied amongst [0.001,0.01,0.1,1,10], and the group number [5,10,15,20,25]. As illustrated in Fig.6, we present the performance in terms of HR@10 and NDCG@10 across the datasets.…”

Section: Sensitivity Analysismentioning

confidence: 99%

“…Some others resort to attribute data of different modalities to mitigate data sparseness. Typical attribute data include user profile [20], descriptive texts [4][5][6], images [18,19], etc. However, these recommender models are tightly coupled with one information source or another, and the requirement of extra information sources limits their scalability.…”

Section: Introductionmentioning

confidence: 99%

DBRec

Wen

Zhong

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

In recommender systems, the user-item interaction data is usually sparse and not sufficient for learning comprehensive user/item representations for recommendation. To address this problem, we propose a novel dual-bridging recommendation model (DBRec). DBRec performs latent user/item group discovery simultaneously with collaborative filtering, and interacts group information with users/items for bridging similar users/items. Therefore, a user's preference over an unobserved item, in DBRec, can be bridged by the users within the same group who have rated the item, or the user-rated items that share the same group with the unobserved item. In addition, we propose to jointly learn user-user group (itemitem group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations. We jointly integrate collaborative filtering, latent group discovering and hierarchical modelling into a unified framework, so that all the model parameters can be learned toward the optimization of the objective function. We validate the effectiveness of the proposed model with two real datasets, and demonstrate its advantage over the state-ofthe-art recommendation models with extensive experiments.

show abstract

LGA: latent genre aware micro-video recommendation on social media

Cited by 33 publications

References 27 publications

Collaborative Filtering Recommendation Algorithm Based on Knowledge Graph

Collaborative Filtering Recommendation Algorithm Based on Knowledge Graph

A Video Recommendation System for Complex Topic Learning Based on a Sustainable Design Approach

DBRec

Contact Info

Product

Resources

About