Video suggestion and discovery for youtube

Baluja, Shumeet; Seth, Rohan; Sivakumar, D.; Yu, Jing; Yagnik, Jay; Kumar, Shankar; Ravichandran, Deepak; Aly, Mohamed

doi:10.1145/1367497.1367618

Cited by 330 publications

(23 citation statements)

References 7 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early works used homogenous graphs, in which nodes denoted items and edges represented inter‐item similarity, for example, (Gori & Pucci, ). Other works modeled bipartite graphs, in which edges connected user nodes to nodes denoting items that they rated (Baluja et al, ; Fouss, Pirotte, Renders, & Saeren, ).…”

Section: Background and Related Workmentioning

confidence: 99%

Graph‐based recommendation integrating rating history and domain knowledge: Application to on‐site guidance of museum visitors

Minkov

Kahanov

Kuflik

2017

Asso for Info Science & Tech

View full text Add to dashboard Cite

Visitors to museums and other cultural heritage sites encounter a wealth of exhibits in a variety of subject areas, but can explore only a small number of them. Moreover, there typically exists rich complementary information that can be delivered to the visitor about exhibits of interest, but only a fraction of this information can be consumed during the limited time of the visit. Recommender systems may help visitors to cope with this information overload. Ideally, the recommender system of choice should model user preferences, as well as background knowledge about the museum's environment, considering aspects of physical and thematic relevancy. We propose a personalized graphbased recommender framework, representing rating history and background multi-facet information jointly as a relational graph. A random walk measure is applied to rank available complementary multimedia presentations by their relevancy to a visitor's profile, integrating the various dimensions. We report the results of experiments conducted using authentic data collected at the Hecht museum. 1 An evaluation of multiple graph variants, compared with several popular and state-of-theart recommendation methods, indicates on advantages of the graph-based approach.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Graph‐based recommendation integrating rating history and domain knowledge: Application to on‐site guidance of museum visitors

Minkov

Kahanov

Kuflik

2017

Asso for Info Science & Tech

View full text Add to dashboard Cite

show abstract

“…This is necessary considering the wide quantity of more than 45 million videos [6]. These graphs can be generated e.g.…”

Section: Related Workmentioning

confidence: 99%

The Future of Teleteaching in MOOC Times

Malchow

Bauer

Meinel

2014

2014 IEEE 17th International Conference on Computational Science and Engineering

View full text Add to dashboard Cite

In the last decades, a lot of different e-learning platforms have established. There are several types of them for example teleteaching platforms. For a couple of years, MOOC platforms have come up and have been enjoying great popularity. In this paper we analyze how important teleteaching platforms are in times of MOOCs. A teleteaching platform is understood as an online service which offers live or recorded lectures as video streams. Furthermore, different concepts how teleteaching can be integrated into MOOC courses are discussed as well as approaches to analyze differences in learning outcome and behavior of students using MOOCs and teleteaching platforms. We analyze if there are urgent factors for the use of teleteaching systems with a view on students' behavior and learn success. It is further discussed how intelligent integration methods can be used to offer students an enhanced learning experience.

show abstract

“…So far, several graph-based recommendation methods have been introduced such as [13] [19][20] [21]. These methods only assume user and item environments in common.…”

Section: Related Workmentioning

confidence: 99%

Random walk based entity ranking on graph for multidimensional recommendation

Lee

Song

Kahng

et al. 2011

Proceedings of the Fifth ACM Conference on Recommender Systems

View full text Add to dashboard Cite

In many applications, flexibility of recommendation, which is the capability of handling multiple dimensions and various recommendation types, is very important. In this paper, we focus on the flexibility of recommendation and propose a graph-based multidimensional recommendation method. We consider the problem as an entity ranking problem on the graph which is constructed using an implicit feedback dataset (e.g. music listening log), and we adapt Personalized PageRank algorithm to rank entities according to a given query that is represented as a set of entities in the graph. Our model has advantages in that not only can it support the flexibility, but also it can take advantage of exploiting indirect relationships in the graph so that it can perform competitively with the other existing recommendation methods without suffering from the sparsity problem.

show abstract

Video suggestion and discovery for youtube

Cited by 330 publications

References 7 publications

Graph‐based recommendation integrating rating history and domain knowledge: Application to on‐site guidance of museum visitors

Graph‐based recommendation integrating rating history and domain knowledge: Application to on‐site guidance of museum visitors

The Future of Teleteaching in MOOC Times

Random walk based entity ranking on graph for multidimensional recommendation

Contact Info

Product

Resources

About