Multimodal Sparse Linear Integration for Content-Based Item Recommendation

Zhu, Qiusha; Li, Zhao; Wang, Haohong; Yang, Yimin; Shyu, Mei‐Ling

doi:10.1109/ism.2013.37

Cited by 10 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…QP Estudos # Q1 [5,7,8,9,16,19,26,27,28,29,30,31] 12 Q2 [5,7,8,9,16,19,23,26,27,28,29,30,31] Em um trabalho de análise mais específico, cada um dos 13 estudos foi detalhadamente analisado para identificação das soluções propostas para construção dos módulos de um SRbC (conforme Figura 1). Os resultados dessa análise estão organizados por módulo nas três próximas seções.…”

Section: Tabela 4: Estudos X Questões De Pesquisa (Qp)unclassified

Aprendizado de Máquina em Sistemas de Recomendação Baseados em Conteúdo Textual: Uma Revisão Sistemática

Brunialti¹,

Peres²,

Freire³

et al. 2015

Anais Do Simpósio Brasileiro De Sistemas De Informação (SBSI)

View full text Add to dashboard Cite

RESUMOSistemas de Recomendação baseados em Conteúdo (SRbC) e umaárea em que estratégias de Aprendizado de Máquina (AM) podem ser potencialmente aplicadas comêxito. Contudo, especificamente naárea de SRbC textual, o uso de AM não tem sido expressivo nosúltimos anos. Neste artigó e apresentada uma Revisão Sistemática para identificação, interpretação e avaliação de como estratégias de AM vêm sendo utilizadas no contexto de SRbC textual a fim de contribuir para a evolução da interseção de taisáreas. Palavras-ChaveABSTRACT Content-based Recommendation Systems (CbRS) is a research area in which Machine Learning (ML) strategies can be applied with success. However, specifically in textual CbRS, the use of ML has not been expressive in recent years. To contribute to the evolution of the intersection of such areas, we present a Systematic Review to identify, interpret and evaluate how the ML strategies have been applied to CbRS.

show abstract

Section: Tabela 4: Estudos X Questões De Pesquisa (Qp)unclassified

Aprendizado de Máquina em Sistemas de Recomendação Baseados em Conteúdo Textual: Uma Revisão Sistemática

Brunialti¹,

Peres²,

Freire³

et al. 2015

Anais Do Simpósio Brasileiro De Sistemas De Informação (SBSI)

View full text Add to dashboard Cite

show abstract

“…Update the diffusion probability k v,w by using Equation 13 if v appears in any diffusion episodes. Otherwise use Equation 12 to update k v,w .…”

Section: A Variance Regularizationmentioning

confidence: 99%

“…Although such a fact has been known for a while [11], [12], [13], previous research efforts have not addressed the implication of such facts. Therefore, when the methods from [7], [8] is used to estimate the diffusion probabilities, many of the diffusion probabilities are estimated as either 0 or 1.0, which is evidence of overfitting.…”

Section: Introductionmentioning

confidence: 99%

Learning the information diffusion probabilities by using variance regularized EM algorithm

Cao

Zhao

2014

2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014)

Self Cite

View full text Add to dashboard Cite

In this paper we address the problem of learning the information diffusion probabilities when there is no sufficient data of information diffusion. By observing the information diffusion behavior on the popular social network web-site Twitter, we find that the evidence of information diffusion is extremely sparse. Less than one percent of tweets are retweeted, which is considered as the most important form of information diffusion evidence on Twitter. Previous research on predicting information diffusion probabilities has failed under such scenarios because the problem of over fitting. To overcome this problem, we first propose to use the variance of the diffusion probabilities as a measure of model complexity for the independent cascade model. After that, we propose two regularization schemes to reduce model complexity. The first scheme is based on regularizing the variance of the diffusion probabilities directly. The second scheme is based on regularizing the mean absolute deviation of the logarithm of the diffusion probabilities. We are able to derive an approximation solution for the first scheme and analytical solution to the second scheme. We conduct experiments by simulating information diffusion on six social network datasets. Experimental results show that the variance regularization scheme outperforms the baseline by a noticeable margin. The mean absolute deviation regularization scheme is better than the baseline.

show abstract

“…In [35], Chen et al propose a fusion strategy to combine ranking scores from both tag-based and content-based models, where the adjustment, reliability, and correlation of ranking scores from different models are all considered. Zhu et al present a Sparse Linear Integration (SLI) model for integrating visual content and its associated metadata (i.e., the content and the context modalities), for the tasks of semantic concept retrieval and content-based video recommendation [36,37]. Furthermore, a method called VideoTopic is proposed for content-based video analysis and recommendation by modeling both textual and visual information [38,39].…”

Section: Multi-modal Multi-layer Fusionmentioning

confidence: 99%

Exploring Hidden Coherent Feature Groups and Temporal Semantics for Multimedia Big Data Analysis

Yang¹

Self Cite

View full text Add to dashboard Cite

Multimodal Sparse Linear Integration for Content-Based Item Recommendation

Cited by 10 publications

References 18 publications

Aprendizado de Máquina em Sistemas de Recomendação Baseados em Conteúdo Textual: Uma Revisão Sistemática

Aprendizado de Máquina em Sistemas de Recomendação Baseados em Conteúdo Textual: Uma Revisão Sistemática

Learning the information diffusion probabilities by using variance regularized EM algorithm

Exploring Hidden Coherent Feature Groups and Temporal Semantics for Multimedia Big Data Analysis

Contact Info

Product

Resources

About