DMCA
Stretching the Life of Twitter Classifiers with Time-Stamped Semantic Graphs
| Citations: | 1 - 0 self |
BibTeX
@MISC{Cano_stretchingthe,
author = {A. Elizabeth Cano and Yulan He and Harith Alani},
title = {Stretching the Life of Twitter Classifiers with Time-Stamped Semantic Graphs},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. 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 classifica-tion is a common technique used for automatically capturing themes that emerge from social media streams. However, such techniques are sensitive to the evo-lution 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 Therefore, traditional supervised classification methods which rely on labelled data could rapidly become outdated.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.
Keyphrases
time-stamped semantic graph twitter classifier social medium ukraine crisis novel transfer automatic topic classification topic classifica-tion new data semantic feature dbpedia graph war conflict effective channel new event-dependent vocabulary classification task previous epoch various challenge common technique feature age traditional supervised classification method current event public opinion topic classifier social medium stream promising result
