Moral Stance Recognition from Text
Overview
Stance recognition is the computational task of determining whether the author of a text (e.g., a publication on social networks) may have a favourable, contrary or neutral attitude (or stance) towards a particular target (e.g., a person, a company, a product, a piece of legislation etc.) Computational models of stance recognition are common in the case of the English language, but much less so in the case of Portuguese. Based on these observations, this project intends to develop a prototype of a system for the recognition of moral and/or ideological stances from Portuguese texts by making use of supervised machine learning methods, whose initial results will be taken as the basis for future studies in this field.
The system prototype (in Portuguese), developed by Wesley Santos, is available HERE - please give it a try!!!
The BRmoral corpus is avaliable from HERE.
Current status
The project ran from April 2019 to April 2020 under USP PRP grant nr. 668/2018.
Publications
Pavan, Matheus Camasmie ; Vitor Garcia dos Santos ; Alex Gwo Jen Lan ; João Trevisan Martins ; Wesley Ramos dos Santos ; Caio Deutsch ; Pablo Botton da Costa ; Fernando Chiu Hsieh ; Ivandré Paraboni (2023) Morality Classification in Natural Language Text. IEEE Transactions on Affective Computing 14(1), pp.857-863. 10.1109/TAFFC.2020.3034050. [corpus]
da Silva, Samuel Caetano ; Thiago Castro Ferreira ; Ricelli Moreira Silva Ramos ; Ivandré Paraboni (2020) Data Driven and Psycholinguistics Motivated Approaches to Hate Speech Detection. Computación y Systemas 24(3), pp. 1179-1188. 10.13053/CyS-24-3-3478.
Pavan, Matheus Camasmie ; Wesley Ramos dos Santos ; Ivandré Paraboni (2020) Twitter Moral Stance Classification using Long Short-Term Memory Networks. 9th Brazilian Conference on Intelligent Systems (BRACIS). Lecture Notes in Artificial Intelligence v. 12319, pp 636-647, Springer, Cham. 10.1007/978-3-030-61377-8_45.
dos Santos, Wesley Ramos; Ivandré Paraboni (2019) Moral Stance Recognition and Polarity Classification from Twitter and Elicited Text. Recent Advances in Natural Language Processing (RANLP-2019), pp. 1069-1075. Varna, Bulgaria. 10.26615/978-954-452-056-4_123.
dos Santos, Wesley Ramos; Ivandré Paraboni (2019) Reconhecimento de posicionamentos de natureza moral em textos. In: STIL-2019 TilIC workshop, 2019, Salvador.