Graph-based Techniques for Topic Classification of Tweets in Spanish

Author
Keywords
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.
Year of Publication
2014
Journal
International Journal of Interactive Multimedia and Artificial Intelligence
Volume
2
Issue
Special Issue on AI Techniques to Evaluate Economics and Happines
Number
5
Number of Pages
31-37
Date Published
03/2014
ISSN Number
1989-1660
Citation Key
URL
http://www.ijimai.org/journal/sites/default/files/files/2014/03/ijimai20142_5_4_pdf_17528.pdf
DOI
10.9781/ijimai.2014.254