In this paper we describe the participation of the WordUp! team in the VaxxStance shared task at IberLEF 2021. The goal of the competition is to determine the author's stance from tweets written both in Spanish and Basque on the topic of the Antivaxxers movement. Our approach, in the four different tracks proposed, combines the Logistic Regression classifier with diverse groups of features: stylistic, tweet-based, user-based, lexicon-based, dependency-based, and network-based. The outcomes of our experiments are in line with state-of-the-art results on other languages, proving the efficacy of combining methods derived from NLP and Network Science for detecting stance in Spanish and Basque.
WordUp! at VaxxStance 2021: Combining Contextual Information with Textual and Dependency-Based Syntactic Features for Stance Detection / Lai, Mirko; Teresa Cignarella, Alessandra; Finos, Livio; Sciandra, Andrea. - 2943:(2021), pp. 210-232. (Intervento presentato al convegno XXXVII International Conference of the Spanish Society for Natural Language Processing. tenutosi a Málaga (Spain) nel 21/09/2021).
WordUp! at VaxxStance 2021: Combining Contextual Information with Textual and Dependency-Based Syntactic Features for Stance Detection.
Andrea Sciandra
2021
Abstract
In this paper we describe the participation of the WordUp! team in the VaxxStance shared task at IberLEF 2021. The goal of the competition is to determine the author's stance from tweets written both in Spanish and Basque on the topic of the Antivaxxers movement. Our approach, in the four different tracks proposed, combines the Logistic Regression classifier with diverse groups of features: stylistic, tweet-based, user-based, lexicon-based, dependency-based, and network-based. The outcomes of our experiments are in line with state-of-the-art results on other languages, proving the efficacy of combining methods derived from NLP and Network Science for detecting stance in Spanish and Basque.File | Dimensione | Formato | |
---|---|---|---|
vaxx_paper3.pdf
Open access
Tipologia:
Versione pubblicata dall'editore
Dimensione
828.41 kB
Formato
Adobe PDF
|
828.41 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris