Stretching the life of Twitter classifiers with time-stamped semantic graphs

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations Save citation


Research units


Social media has become an effective channel for communicating both trends and public opinion on current events. However the automatic topic classification of social media content pose various challenges. Topic classification is a common technique used for automatically capturing themes that emerge from social media streams. However, such techniques are sensitive to the evolution of topics when new event-dependent vocabularies start to emerge (e.g., Crimea becoming relevant to War Conflict during the Ukraine crisis in 2014). Therefore, traditional supervised classification methods which rely on labelled data could rapidly become outdated. In this paper we propose a novel transfer learning approach to address the classification task of new data when the only available labelled data belong to a previous epoch. This approach relies on the incorporation of knowledge from DBpedia graphs. Our findings show promising results in understanding how features age, and how semantic features can support the evolution of topic classifiers.

Request a copy

Request a copy


Publication date31 Dec 2014
Publication titleThe Semantic Web – ISWC 2014 : 13th International Semantic Web Conference, Riva del Garda, Italy, October 19-23, 2014, proceedings, part II
EditorsPeter Mika, Tania Tudorache, Abraham Bernstein, Chris Welty, et al
Place of PublicationChem (CH)
Number of pages17
ISBN (Electronic)978-3-319-11915-1
ISBN (Print)978-3-319-11914-4
Original languageEnglish
Event13th International Semantic Web Conference - Riva del Garda, Italy
Duration: 19 Oct 201423 Oct 2014

Publication series

NameLecture notes in computer science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference13th International Semantic Web Conference
Abbreviated titleISWC 2014
CityRiva del Garda


  • concept drift, DBpedia, feature relevance decay, social media, topic detection

Employable Graduates; Exploitable Research

Copy the text from this field...