UninaStudents @ SardiStance: Stance Detection in Italian Tweets - Task A

التفاصيل البيبلوغرافية
العنوان: UninaStudents @ SardiStance: Stance Detection in Italian Tweets - Task A
المؤلفون: Moraca, Maurizio, Sabella, Gianluca, Morra, Simone
بيانات النشر: Accademia University Press, 2021.
سنة النشر: 2021
مصطلحات موضوعية: Language & Linguistics, Automatic Misogyny Identification, AlBERTo, BERT Model, Language Game ``La Ghigliottina'', MEME management, EVALITA, Convolutional Neural Network, LAN000000, Hate Speech Detection, CBX, linguistica computazionale, Misogyny on Twitter Posts, COVID-19 Infodemic, Multimodal Meme Detection
الوصف: This document describes a classification system for the SardiStance task at EVALITA 2020. The task consists in classifying the stance of the author of a series of tweets towards a specific discussion topic. The resulting system was specifically developed by the authors as final project for the Natural Language Processing class of the Master in Computer Science at University of Naples Federico II. The proposed system is based on an SVM classifier with a radial basis function as kernel making use of features like 2 char-grams, unigram hashtag and Afinn weight computed on automatic translated tweets. The results are promising in that the system performances are on average higher than that of the baseline proposed by the task organizers. Questo documento descrive un sistema di classificazione per il task SardiStance di EVALITA 2020. Il task consiste nel classificare la posizione dell’autore di una serie di tweets nei confronti di uno specifico topic di discussione. Il sistema risultante è stato specificamente sviluppato dagli autori come progetto finale per il corso di Elaborazione del Linguaggio Naturale nell’ambito del corso di laurea magistrale in Informatica presso l’università degli studi di Napoli Federico II. Il sistema qui proposto si basa su un classificatore SVM con una funzione radiale di base come kernel facendo uso di features come 2 char-grams, unigram hashtag e l’Afinn weight calcolato sui tweet tradotti in automatico. I risultati sono promettenti in quanto le performance sono in media superiori rispetto a quelle della baseline proposta dagli organizzatori del task.
اللغة: English
URL الوصول: https://explore.openaire.eu/search/publication?articleId=openedition_::3243a4323b54762133da8db9ef35337f
http://books.openedition.org/aaccademia/7189
حقوق: OPEN
رقم الأكسشن: edsair.openedition...3243a4323b54762133da8db9ef35337f
قاعدة البيانات: OpenAIRE