Grant: Engage Grants Program
Dalhousie University
$24,960.00
Automatic Tagging and Recommendation of News Articles using Wikipedia
EF 2014-15
Résumé
In today' digital era, it is more important than ever before for the Chronicle Herald to stand by its motto of""Connecting you to what matters"". Defining the ""what matters"" is the key challenge. Are you interested in anynews about Nova Scotia Power, your kid's hockey team, the weather, municipal politics, etc. When is the besttime to offer short news briefs and context of what to expect that day? When and on what device are peoplereading long form journalism? What topics keep you reading longer? If we presented more of what you want,would you now make more time to read it - would you simply get lost in time and stick with the experience?Recommender systems have been around for a long time. Dating services, Amazon.com, Netflix and Applehave all worked on relevancy algorithms to ensure that perfect match. We need to discover and amplify theconnection between reader and content. Profile building and predicting what the person's next move will be iskey to the future of the news industry. Having customers more engaged and deeply entrenched in the contentwill come when we provide them with more content they want to read, hear and view in the form they expecton the particular device or medium they are engaged with at the time.The Chronicle Herald has more and more data being collected on its subscribers and on-line readers. It istime to start using this data to begin recommending what matters to the individual based on the informationthey provide and the behaviours they portray at the same time finding the trends in relevant social space to putcontent in front of folk before anyone else knows.This project aims to build the foundation for connecting readers with news by automatically assigning tagsto news by making use of Wikipedia, the collaboratively built, multilingual, hyperlinked, on-line encyclopedicknowledge base.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Nova Scotia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
468860-2014
Name nom
Shepherd, Michael
Department département
Computer Science, Faculty of
Organization id
79
Institution établissement
Dalhousie University
Province en
Nova Scotia
Province fr
Nouvelle-Écosse
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2014
Award amount
24960
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1551
Committee name en
Atlantic Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Atlantique
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2710
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information systems design
Research subject fr
Conception de systèmes d'information
Partie
1
Nb partie
1
Application title
Automatic Tagging and Recommendation of News Articles using Wikipedia
Keyword
NSERC
Application summary
In today' digital era, it is more important than ever before for the Chronicle Herald to stand by its motto of""Connecting you to what matters"". Defining the ""what matters"" is the key challenge. Are you interested in anynews about Nova Scotia Power, your kid's hockey team, the weather, municipal politics, etc. When is the besttime to offer short news briefs and context of what to expect that day? When and on what device are peoplereading long form journalism? What topics keep you reading longer? If we presented more of what you want,would you now make more time to read it - would you simply get lost in time and stick with the experience?Recommender systems have been around for a long time. Dating services, Amazon.com, Netflix and Applehave all worked on relevancy algorithms to ensure that perfect match. We need to discover and amplify theconnection between reader and content. Profile building and predicting what the person's next move will be iskey to the future of the news industry. Having customers more engaged and deeply entrenched in the contentwill come when we provide them with more content they want to read, hear and view in the form they expecton the particular device or medium they are engaged with at the time.The Chronicle Herald has more and more data being collected on its subscribers and on-line readers. It istime to start using this data to begin recommending what matters to the individual based on the informationthey provide and the behaviours they portray at the same time finding the trends in relevant social space to putcontent in front of folk before anyone else knows.This project aims to build the foundation for connecting readers with news by automatically assigning tagsto news by making use of Wikipedia, the collaboratively built, multilingual, hyperlinked, on-line encyclopedicknowledge base.