Abstract

News can be made more relevant to readers by customising its content. Information Augmentation (IA) combines continuous information streams, like a financial news service, with selected data from heterogeneous information sources. These can be internal databases of any user community, or external resources like encyclopaedia and web search engines. Professional editors add semantic metadata to information flow when the content has been created. Data resources for augmentation are modelled with descriptive metadata and monitored by information mediators. Rich and dynamically changing user and community models are gathered. These models consist of the special interests, expertise level, previous activity, and community context, of any individual user. The personalisation and augmentation process is implemented with an agent-based architecture, which consists of profiling, mediation, and augmentation agents. The profiling agent monitors individual users and user communities. The mediator agent connects various types of data resources and combines data into a XML based format used in augmentation. Augmentation agents receive necessary information from the mediator agent, and present the news context for the reader. The augmentation tools that have been built for the domain of financial news include (1) historical news context; (2) an explanation of financial terms; (3) number comparison; (4) company tracking; and (5) news map.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.