TY - JOUR
T1 - Profiling Fake News Spreaders using Characters and Words N-grams Notebook for PAN at CLEF 2020
AU - Espinosa, Daniel Yacob
AU - Gómez-Adorno, Helena
AU - Sidorov, Grigori
N1 - Publisher Copyright:
Copyright © 2020 for this paper by its authors.
PY - 2020
Y1 - 2020
N2 - With the use of social networks as mass media; The spread of fake news becomes an investigative problem. This article describes our approach to the PAN 2020 task on "Profiling Fake News Spreaders on Twitter" [7]. The objective is to distinguish which users share fake news. Our approach includes a data cleaning part and feature extraction using N-grams of characters and words. The experiments were carried out with different N-gram structures depending on the languages: English and Spanish. We experimented machine learning algorithm Support Vector Machines (libSVM).
AB - With the use of social networks as mass media; The spread of fake news becomes an investigative problem. This article describes our approach to the PAN 2020 task on "Profiling Fake News Spreaders on Twitter" [7]. The objective is to distinguish which users share fake news. Our approach includes a data cleaning part and feature extraction using N-grams of characters and words. The experiments were carried out with different N-gram structures depending on the languages: English and Spanish. We experimented machine learning algorithm Support Vector Machines (libSVM).
UR - http://www.scopus.com/inward/record.url?scp=85113458264&partnerID=8YFLogxK
M3 - Artículo de la conferencia
AN - SCOPUS:85113458264
SN - 1613-0073
VL - 2696
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
T2 - 11th Conference and Labs of the Evaluation Forum, CLEF 2020
Y2 - 22 September 2020 through 25 September 2020
ER -