Towards Social semantic journalism

Copyright 2011 Digital Enterprise Research Institute. All rights reserved.

Digital Enterprise Research Institute www.deri.ie

Enabling Networked Knowledge

Towards Social Semantic Journalism

Bahareh R. Heravi, Marie Boran, John Breslin

{Bahareh.Heravi, M.Boran, John.Breslin}@deri.orgWorkshop on the Potential of Social Media Tools and Data in the News Media Industry (SocMedNews)

ICWSM 2012 – June 2012, Dublin



About DERI

Largest Semantic Web research centre in the world

Number one in its core space Research Publications > 950 Participate in 17 standardisation groups (W3C, OASIS) Approx 140 members from 30 nations

Founded June 2003 Link scientists and engineers / academia and industry Fundamental research Development of Irish-based technology companies Attract industry Education & outreach

Total Research Grants: >€60 million SFI, EU Framework, Enterprise Ireland, Industry



Journalism



Traditional Journalism



Everything is getting Social

User Generated Content is changing the way news stories are produced.



Journalism Today

The audience - citizen journalists - are now a readily available source of news.

The UGC comes from variety of Social Web sources, e.g. Twitter, Facebook, Google+, Flickr, YouTube, blogs, etc.

Vast amount of the UGC could be produced in the event of a breaking news.



UGC

The UGC is even more important when broadcasters have to rely mostly on the Social Web as journalists are restricted to work in certain countries or where there is a danger for them.

The UGC producers would have to spend a considerable amount of time searching, compiling and verifying the material received on the Social Web.

Speed is a killer when there is a breaking news!



Sources to be processed



Challenges

Navigation of data: platforms are not connected and communities are often disparate. The manual process of checking through UGC is

overwhelming and inadequate.

This information lacks exchangeable semantics and thus is not as usable as it can be for creating trustworthy news stories.

Vetting process.



The Social Semantic web



We need a way to connect these islands

image from pidgintech.com

Semantic Web



Semantic Web

The WEB is a network of interlinked Documents accessed via the Internet. Hyperlinks connect these documents

The SEMANTIC WEB is an extension of the current Web, which is about interlinking THINGS.

Unstructured Data Structured Data

Web of Documents Web of Data

Current Web vs. Semantic Web



Aims of the Semantic Web

Bridging the gap between a Web of Documents to a Web of Data, with typed objects and typed relationships.

Adding machine-readable metadata to existing content, so that information can be parsed, queried and reused.

Defining shared semantics for this metadata to allow interoperability between applications.

Enabling machine-readable knowledge at Web scale, making information more easy to find and process.



Social Semantic Web

Bringing the Social web to its full potential



Semantic Interlinking Of Online Community

Sites An effort from DERI to discover how we can

create and establish ontologies on the Semantic Web

Goal of the SIOC ontology is to address interoperability issues on the (Social) Web

Just won the 7-year impact award at Extended Semantic Web Conference 2012.

http://sioc-project.org


Enabling Networked Knowledge16

SIOC



Friend Of A Friend

An ontology for describing people and the relationships that exist between them:

Identity, personal profiles and social networks

http://foaf-project.org/

http://foaf-project.org/



SIOC + FOAF



Social Semantic Journalism



Social Semantic Journalism



Focus of the project

Exploring the ways in which Semantic Web technologies and ontologies, such as SIOC and FOAF, in conjunction with news representation standards, such as rNews, could assist in the process of interlinking online user communities and the UGC for news gathering and verification.

Considers extending/customising SIOC for its utilisation in journalism and the news industry.



Relevant Vocabularies and Initiatives

BBC Programmes Ontology Press.Net News Ontology rNews Schema.org …

NewsWhip Storyful Storify …



Future Research

Literature review on the current utilisation of the Social Web within the news industry.

Literature review on the ways in which Semantic Web technologies have been implemented within the news industry.

Evaluating existing relevant ontologies and data standards within a journalistic context.

Determining what existing Semantic Web tools can be integrated into this project.

Defining a set of contextual factors for assessing trust levels.

Proposing a standard for integration and display of semantically enriched social media content.

Integration with Schema.org



Thank you

Bahareh R. [email protected]

@Bahareh360

mailto:[email protected]

Towards Social semantic journalism

News & Politics