Graph-based Techniques for Topic Classification of Tweets in Spanish

TitleGraph-based Techniques for Topic Classification of Tweets in Spanish
Publication TypeJournal Article
Year of Publication2014
AuthorsCordobés, H., A. Fernández Anta, L. F. Chiroque, F. Pérez, T. Redondo, and A. Santos
JournalInternational Journal of Interactive Multimedia and Artificial Intelligence
ISSN1989-1660
IssueSpecial Issue on AI Techniques to Evaluate Economics and Happines
Volume2
Number5
Date Published03/2014
Pagination31-37
Abstract

Topic classification of texts is one of the most interesting challenges in Natural Language Processing (NLP). Topic classifiers commonly use a bag-of-words approach, in which the classifier uses (and is trained with) selected terms from the input texts. In this work we present techniques based on graph similarity to classify short texts by topic. In our classifier we build graphs from the input texts, and then use properties of these graphs to classify them. We have tested the resulting algorithm by classifying Twitter messages in Spanish among a predefined set of topics, achieving more than 70% accuracy.

KeywordsClassification, Graphs, Happiness, NLP, Text Classification, Topic Classification
DOI10.9781/ijimai.2014.254
URLhttp://www.ijimai.org/journal/sites/default/files/files/2014/03/ijimai20142_5_4_pdf_17528.pdf
AttachmentSize
IJIMAI20142_5_4.pdf585.42 KB