Multimedia content recommendation engine with automatic inference of user preferences

Ferman, A. Mufit; Beek, Peter van der; Errico, James H.; Mi, Sezan

doi:10.1109/icip.2003.1247178

Cited by 8 publications

(7 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ferman et al introduced in [4] novel algorithms for the creation of user profiles based on the usage history and for content filtering. The algorithms are designed to support MPEG-7 as well as TV-Anytime metadata descriptions.…”

Section: Related Workmentioning

confidence: 99%

A user profile-based personalization system for digital multimedia content

Weiß

Scheuerer

Wenleder

et al. 2008

Proceedings of the 3rd International Conference on Digital Interactive Media in Entertainment and Arts

View full text Add to dashboard Cite

With the steadily increasing amount of digital multimedia content, the user will be more and more overstrained. This applies to content being permanently available like videos of online video services as well as broadcast content like in the TV or radio domain. A promising solution for this problem is personalization. In the context of this paper, we refer to the selection and recommendation of content with respect to user's interests and preferences as personalization. These recommendations can either be presented to the user herself or be further used by services like a personalized electronic program guide (EPG) in the TV domain or for automated and personalized selection of content of online video services. This paper introduces an approach to personalize digital multimedia content based on user profile information. For this, two main mechanisms were developed: a profile generator that automatically creates user profiles representing the user preferences, and a content-based recommendation algorithm that estimates the user's interest in unknown content by matching her profile to metadata descriptions of the content. Both features are integrated into a personalization system.

show abstract

Section: Related Workmentioning

confidence: 99%

A user profile-based personalization system for digital multimedia content

Weiß

Scheuerer

Wenleder

et al. 2008

Proceedings of the 3rd International Conference on Digital Interactive Media in Entertainment and Arts

View full text Add to dashboard Cite

show abstract

“…When the user logs in to the system for the first time, he fills out a TV preferences form, which allows him to specify a small number of preferences: genre, personages and channels of interest. Ferman et al [6,7] propose a profiling agent for automatically determining user profiles from content usage history and a filtering agent for automatically filtering content based on the profiles. Fuzzy inferencing is used to construct and update preferences based on content interactions over a period of time (usage history).…”

Section: Closing the Mpeg-7 Content-user Gap?mentioning

confidence: 99%

“…The Event DS is used so that the dynamic spatial relationship preferences are specified via the SpatialRelation CS within the context of the encompassing event. The strength attribute Second, the first half of the next Semantic DS is used to group preferred objects within an event together, also defined by (7). The Object DS encapsulates dynamic preferences for a single object within an event via one or more Relation elements of type agentOf appended with the strength attribute.…”

Section: Type 1 Mpeg-7 User Modelmentioning

confidence: 99%

Closing the content-user gap in MPEG-7: the hanging basket model

Agius

Angelides

2007

Multimedia Systems

View full text Add to dashboard Cite

MPEG-7 is the leading standard for multimedia metadata creation, providing a vast array of description tools. Nevertheless, there exists a disparity between the content models and user models that may be created by the standard: metadata for content models is wide ranging and structured, but metadata for user models only support the specification of an extremely limited range of preferences where content metadata cannot be fully exploited. This results in a very incomplete mapping of user models to content models which we term the MPEG-7 content-user gap. We present a hanging basket model that closes the content-user gap by considering user models to be isomorphic to content models and thus enabling both models to be represented through MPEG-7 content description tools, specifically those concerned with events, objects and properties.

show abstract

“…A body of recent research has investigated the application of MPEG-7 user modelling tools. For TV and broadcasting, approaches have ranged from asking users to fill out a form specifying a small number of preferences, such as genre and channels of interest [3], to using fuzzy inferencing to construct and update user preferences regarding genre, language and broadcast channel based on usage history [4]. Taking clients and networks into account, Martínez et al [5] use ClassificationPreferences and CreationPreferences for filtering content, after which SourcePreferences are used for finding a suitable content variation, while Steiger et al [6] acquire initial prioritisation of user preferences for categories such as content topic, language and source via a form, which is then stored using the UserPreferences DS and updated automatically via the UsageHistory DS by giving higher priority to content categories that are often selected or by adding them to the initial preferences.…”

Section: User Modelling In Mpeg-7mentioning

confidence: 99%

Enriching MPEG-7 User Models with Content Metadata

Agius¹,

Angelides²

2006

2006 First International Workshop on Semantic Media Adaptation and Personalization (SMAP'06)

View full text Add to dashboard Cite

MPEG-7 is an XML-based standard that provides tools for creating rich and structured multimedia content metadata. However, only an extremely limited range of preferences can be specified for user models and multimedia content metadata created by other parts of the standard cannot be fully exploited. This results in a very incomplete mapping of user models to content models. We present an approach to address the problem by representing user models by means of existing MPEG-7 content description tools.

show abstract

Multimedia content recommendation engine with automatic inference of user preferences

Cited by 8 publications

References 1 publication

A user profile-based personalization system for digital multimedia content

A user profile-based personalization system for digital multimedia content

Closing the content-user gap in MPEG-7: the hanging basket model

Enriching MPEG-7 User Models with Content Metadata

Contact Info

Product

Resources

About