ClassStrength v2: An Adaptive Multilingual Tool for Tweet Classification

Diana Cremarenco, Walid Magdy

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

Abstract

In this paper we present the second version of our multilingual tweet classification tool. ClassStrength v2 classifies tweets into 14 categories (Sports, Music, News&Politics etc.) using a distant supervision approach. The new version extends the initial set of five languages to ten (English, French, German, Chinese, Japanese, Arabic, Russian, Spanish, Portuguese and Polish). In addition, the classification models of each language get automatically updated every month to allow accurate classification over time. Our experimentation showed that the larger the time gap between the tweet and the data used for training the model, the worse the performance, which motivated for creating an adaptive version of ClassStrength that get its models updated periodically.
Original languageEnglish
Title of host publication 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages605-608
Number of pages4
ISBN (Electronic)978-1-5386-6051-5
ISBN (Print)978-1-5386-6052-2
DOIs
Publication statusPublished - 25 Aug 2018
Event2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining - Barcelona, Spain
Duration: 28 Aug 201831 Aug 2018
http://asonam.cpsc.ucalgary.ca/2018/index.php

Publication series

Name
PublisherIEEE
ISSN (Print)2473-9928
ISSN (Electronic)2473-991X

Conference

Conference2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining
Abbreviated titleASONAM 2018
Country/TerritorySpain
CityBarcelona
Period28/08/1831/08/18
Internet address

Fingerprint

Dive into the research topics of 'ClassStrength v2: An Adaptive Multilingual Tool for Tweet Classification'. Together they form a unique fingerprint.

Cite this