Automatic metadata enrichment in news production

Mannens, Erik; Troncy, Raphaël; Braeckman, Karel; Deursen, Davy Van; Lancker, Wim Van; Sutter, Renaat De; Walle, Rik Van de

doi:10.1109/wiamis.2009.5031432

“…Early work (Kosch et al 2005;Ohtsuki et al 2006;Smith and Schirling 2006) provides design principles for a metadata life cycle management and demonstrates the value of wellstructured metadata for indexing and compiling multimedia documents across various modalities like text, speech and video. More recent approaches investigate the benefits of ontologies in organising and reutilising semantic metadata for purposes such as metadata enrichment (Hu et al 2009;Mannens et al 2009), collaborative tagging practices (Kim et al 2008) or adaptive content services (Yu et al 2010).…”

Section: Linked Data In the Content Value Chainmentioning

confidence: 99%

Semantic metadata in the publishing industry – technological achievements and economic implications

Pellegrini

¹

2016

View full text Add to dashboard Cite

This paper discusses the adoption of new data management practices, known as Linked Data, by publishing companies from a strategic management perspective. It investigates the role of semantic metadata in the creation and exploitation of so called Linked Data ecosystems and discusses organizational effects on business and value creation processes stimulated by the technology. The theoretical assumptions are complemented by two case studies that provide insights how publishing companies use Linked Data technologies to diversify their business, strategically position themselves within emerging business ecosystems and adapt to the affordances of advanced data management practices. The analysis reveals that despite of differences in the adoption strategy both publishing companies have identified Linked Data technologies as the core of their innovation strategy having a profound impact on existing business practices and new strategies of value creation.

show abstract

“…Extension to other standards is cumbersome since it is hard to state the equivalence between two XML elements. EBU (amongst others) have proposed to model an OWL ontology of NewsML-G2 4 to address these shortcomings and we have discussed the design decisions regarding its modelling from existing XML Schemas [33,21].…”

Section: News Modellingmentioning

confidence: 99%

“…We have shown how such an up-to-date news bulletin can be dynamically created and personalized to match the consumer's static categories preferences [10,21] by merging different news sources and using the NewsML-G2 specification [15]. While the impact of file-based production indeed mainly affected the work methods of the news production staffjournalists, anchors, editorial staff, etc - [20,9], the added-value for the end-user was still marginal, id est, he might notice that news content is made available faster.…”

Section: Introductionmentioning

confidence: 99%

Automatic news recommendations via aggregated profiling

Mannens

¹

,

Coppens

²

,

Pessemier

³

et al. 2011

Multimed Tools Appl

View full text Add to dashboard Cite

Today, people have only limited, valuable leisure time at their hands which they want to fill in as good as possible according to their own interests, whereas broadcasters want to produce and distribute news items as fast and targeted as possible. These (developing) news stories can be characterised as dynamic, chained, and distributed events in addition to which it is important to aggregate, link, enrich, recommend, and distribute these news event items as targeted as possible to the individual, interested user. In this paper, we show how personalised recommendation and distribution of news events, described using an RDF/OWL representation of the NewsML-G2 standard, can be enabled by automatically categorising and enriching news events metadata via smart indexing and linked open datasets available on the web of data. The recommendations -based on a global, aggregated profile, which also takes into account the (dis)likings of peer friends -are finally fed to the user via a personalised RSS feed. As such, the ultimate goal is to provide an open, user-friendly recommendation platform that harnesses the end-user with a tool to access useful news event information that goes beyond basic information retrieval. At the same time, we provide the (inter)national community with standardised mechanisms to describe/distribute news event and profile information.

show abstract

“…Extension to other standards is cumbersome since it is hard to state the equivalence between two XML elements. EBU (amongst others) have proposed to model an OWL ontology of NewsML-G2 6 to address these shortcomings and we have discussed the design decisions regarding its modeling from existing XML Schemas [10].…”

Section: News Modellingmentioning

confidence: 99%

“…In particular, we automated the production of multiple versions of news bulletins for different consumption platforms since news broadcasters generally aggregate and produce more material than is required for broadcast or online distribution. We have shown how such an up-to-date news bulletin can be dynamically created and personalized to match the consumer's static categories preferences [10] by merging different news sources and using the NewsML-G2 specification 2 . While the impact of file-based production indeed mainly affected the work methods of the news production staff -journalists, anchors, editorial staff, etc - [9], the added-value for the end-user was still marginal, id est, he might notice that news content is made available faster.…”

Section: Introductionmentioning

confidence: 99%

Automatic news recommendations via profiling

Mannens

¹

,

Coppens

²

,

Pessemier

³

et al. 2010

Proceedings of the 3rd International Workshop on Automated Information Extraction in Media Production

View full text Add to dashboard Cite

Today, people have only limited, valuable leisure time at their hands which they want to fill in as good as possible according to their own interests, whereas broadcasters want to produce and distribute news items as fast and targeted as possible. These (developing) news stories can be characterised as dynamic, chained, and distributed events in addition to which it is important to aggregate, link, enrich, recommend, and distribute these news event items as targeted as possible to the individual, interested user. In this paper, we show how personalised recommendation and distribution of news events, described using an RDF/OWL representation of the NewsML-G2 standard, can be enabled by automatically categorising and enriching news events metadata via smart indexing and linked open datasets available on the web of data. The recommendations -based on a global, aggregated profile, which also takes into account the (dis)likings of peer friends -are finally fed to the user via a personalised RSS feed. As such, the ultimate goal is to provide an open, user-friendly recommendation platform that harnesses the end-user with a tool to access useful news event information that goes beyond basic information retrieval. At the same time, we provide the (inter)national community with standardised mechanisms to describe/distribute news event and profile information.

show abstract

Automatic metadata enrichment in news production

Cited by 9 publications

References 11 publications

Semantic metadata in the publishing industry – technological achievements and economic implications

Semantic metadata in the publishing industry – technological achievements and economic implications

Automatic news recommendations via aggregated profiling

Automatic news recommendations via profiling

Contact Info

Product

Resources

About