Movie Recommendation Based on Graph Traversal Algorithms

Demovic, Lubos; Fritscher, Eduard; Kriz, Jakub; Kuzmik, Ondrej; Proksa, Ondrej; Vandlikova, Diana; Zelenik, Dusan; Bieliková, Mária

doi:10.1109/dexa.2013.24

Cited by 10 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method can be also used with the data in a time window, this enable to follow the changes in the user profile in relation to movies. An effect that is known to occur [4].…”

Section: Discussionmentioning

confidence: 99%

“…Regarding the type of filtering, we implemented a nearest neighbor technique. Demovic et al [4] apply a content-based filtering, Bellogin and Parapar [1] uses collaborative filtering and Lee et al [6] uses hybrid recommendation which combines both approaches. To provide the best recommendation, In the proposed approach the responses are ranked in the same way as Lee et al [6].…”

Section: Related Workmentioning

confidence: 99%

“…Similar to [1,4,6], we also make use of graphs with more than one type of vertex. The concept of grouping vertices is used, which is also applied by [1,6].…”

Section: Related Workmentioning

confidence: 99%

“…Demovic et al [4] proposed a recommendation system modeled as a graph with three types of nodes: user, movie and gender. They considered the possible changes of the user's interest in relation to the type of film, for example, on Sunday the user can prefer to watch a comedy movie, instead of watching documentaries which he usually watch during the week.…”

Section: Related Workmentioning

confidence: 99%

“…They considered the possible changes of the user's interest in relation to the type of film, for example, on Sunday the user can prefer to watch a comedy movie, instead of watching documentaries which he usually watch during the week. The four recommendation algorithms presented in [4] start from the initial nodes that can be explicitly described by the user or inferred by the system, e.g. the genres of movie he wants to watch.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Recommender System Based on Modularity

Sibaldo

Carvalho

Ren

et al. 2014

Proceedings of the 2014 Recommender Systems Challenge

View full text Add to dashboard Cite

This paper presents a solution for the RecSys Challenge 2014 by performing a clustering in a bipartite graph whose vertices are of two types: user and item, having the edges as the engagement given to a tweet. The Modularity metric, which is well-known in the area of complex networks to quantify how good the groups of nodes are defined in the network, was used to form the groups that contain users and movies that are closely related. The resulting groups have members of both classes of vertices. From this clustering, a nearest neighbor technique was applied to rank the tweets by the engagement.

show abstract

“…The proposed method can be also used with the data in a time window, this enable to follow the changes in the user profile in relation to movies. An effect that is known to occur [4].…”

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…Similar to [1,4,6], we also make use of graphs with more than one type of vertex. The concept of grouping vertices is used, which is also applied by [1,6].…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Recommender System Based on Modularity

Sibaldo

Carvalho

Ren

et al. 2014

Proceedings of the 2014 Recommender Systems Challenge

View full text Add to dashboard Cite

show abstract

Second Screen User Profiling and Multi-level Smart Recommendations in the Context of Social TVs

Valsamis¹,

Psychas²,

Aisopos³

et al. 2017

Emerging Technologies for Education

View full text Add to dashboard Cite

In the context of Social TV, the increasing popularity of first and second screen users, interacting and posting content online, illustrates new business opportunities and related technical challenges, in order to enrich user experience on such environments. SAM (Socializing Around Media) project uses Social Media-connected infrastructure to deal with the aforementioned challenges, providing intelligent user context management models and mechanisms capturing social patterns, to apply collaborative filtering techniques and personalized recommendations towards this direction. This paper presents the Context Management mechanism of SAM, running in a Social TV environment to provide smart recommendations for first and second screen content. Work presented is evaluated using real movie rating dataset found online, to validate the SAM's approach in terms of effectiveness as well as efficiency.

show abstract

Efficient Context Management and Personalized User Recommendations in a Smart Social TV Environment

Aisopos

Valsamis²,

Psychas

et al. 2017

Economics of Grids, Clouds, Systems, and Services

View full text Add to dashboard Cite

Abstract. With the emergence of Smart TV and related interconnected devices, second screen solutions have rapidly appeared to provide more content for end-users and enrich their TV experience. Given the various data and sources involved -videos, actors, social media and online databases-the aforementioned market poses great challenges concerning user context management and sophisticated recommendations that can be addressed to the end-users. This paper presents an innovative Context Management model and a related first and second screen recommendation service, based on a user-item graph analysis as well as collaborative filtering techniques in the context of a Dynamic Social & Media Content Syndication (SAM) platform. The model evaluation provided is based on datasets collected online, presenting a comparative analysis concerning efficiency and effectiveness of the current approach, and illustrating its added value.

show abstract

Movie Recommendation Based on Graph Traversal Algorithms

Cited by 10 publications

References 9 publications

Recommender System Based on Modularity

Recommender System Based on Modularity

Second Screen User Profiling and Multi-level Smart Recommendations in the Context of Social TVs

Efficient Context Management and Personalized User Recommendations in a Smart Social TV Environment

Contact Info

Product

Resources

About