Efficient Social Network Multilingual Classification using Character, POS n-grams and Dynamic Normalization
Information Retrieval
2017-02-22 v1 Computation and Language
Social and Information Networks
Abstract
In this paper we describe a dynamic normalization process applied to social network multilingual documents (Facebook and Twitter) to improve the performance of the Author profiling task for short texts. After the normalization process, -grams of characters and n-grams of POS tags are obtained to extract all the possible stylistic information encoded in the documents (emoticons, character flooding, capital letters, references to other users, hyperlinks, hashtags, etc.). Experiments with SVM showed up to 90% of performance.
Cite
@article{arxiv.1702.06467,
title = {Efficient Social Network Multilingual Classification using Character, POS n-grams and Dynamic Normalization},
author = {Carlos-Emiliano González-Gallardo and Juan-Manuel Torres-Moreno and Azucena Montes Rendón and Gerardo Sierra},
journal= {arXiv preprint arXiv:1702.06467},
year = {2017}
}
Comments
8 pages, 6 figures, Conference paper