UlyssesSD-Br: Stance Detection in Brazilian Political Polls

被引：0

作者：

Maia, Dyonnatan F. ^{[1
]}

Silva, Nadia F. F. ^{[1
]}

Souza, Ellen P. R. ^{[2
]}

Nunes, Augusto S. ^{[3
]}

Procopio, Lucas C. ^{[3
]}

Sampaio, Guthemberg da S. ^{[2
]}

Dias, Marcio de S. ^{[3
,4
]}

Alves, Adrio O. ^{[3
]}

Maia, Dyessica F. ^{[6
]}

Ribeiro, Ingrid A. ^{[7
]}

Pereira, Fabiola S. F. ^{[5
]}

de Carvalho, Andre P. de L. F. ^{[3
]}

机构：

[1] Univ Fed Goias, Inst Informat, Goiania, Go, Brazil

[2] Univ Fed Pernambuco, Ctr Informat, Recife, PE, Brazil

[3] Univ Sao Paulo, Inst Math & Comp Sci, Sao Carlos, SP, Brazil

[4] Fed Univ Catalao, Catalao, Go, Brazil

[5] Univ Fed Uberlandia, Uberlandia, MG, Brazil

[6] Pontifical Catholic Univ Goias, Goiania, Go, Brazil

[7] Univ Brasilia, Fac Ceilandia, Brasilia, DF, Brazil

来源：

PROGRESS IN ARTIFICIAL INTELLIGENCE, EPIA 2022 | 2022年 / 13566卷

关键词：

Stance detection; Political comments; Cross-target;

D O I：

10.1007/978-3-031-16474-3_8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Political bill comments published in digital media may reveal the issuer's stances. Through this, we can identify and group the polarity of these public opinions. The automatic stance detection task involves viewing the text and the target topic. Due to the diversity and emergence of new bills, the challenge approached is to estimate the polarity of a new topic. Thus, this paper evaluates cross-target stance detection with many-to-one approaches in a collected Portuguese dataset of the political pool from the Brazilian Chamber of Deputies website. We proposed a new corpus for the bills' opinion domain and tested it in several models, where we achieved the best result with the mBERT model in classification with the joint input topic and comment method. We verify that the mBERT model successfully handled cross-target tasks with this corpus among the tested algorithms.

引用

页码：85 / 95

页数：11

共 13 条

[1] Allaway Emily, 2020, P 2020 C EMPIRICAL M, P8913, DOI DOI 10.18653/V1/2020.EMNLP-MAIN.717
[2] Allaway Emily, 2021, P 2021 C N AM CHAPTE, P4756, DOI DOI 10.18653/V1/2021.NAACL-MAIN.379
[3] Conforti C, 2020, 58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), P1715
[4] Devlin J, 2019, Arxiv, DOI arXiv:1810.04805
[5] dos Santos W. R., 2019, RECENTS ADV NATURAL, P1069, DOI [DOI 10.26615/978-954-452-056-4_123, DOI 10.26615/978-954-452-056-4123]
[6] Mohammad S., 2016, Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), P31, DOI [10.18653/v1/S16-1003, DOI 10.18653/V1/S16-1003]
[7] Stance and Sentiment in Tweets
Mohammad, Saif M.
Sobhani, Parinaz
Kiritchenko, Svetlana
[J]. ACM TRANSACTIONS ON INTERNET TECHNOLOGY, 2017, 17 (03)
[8] Pavan Matheus Camasmie, 2020, Intelligent Systems. 9th Brazilian Conference, BRACIS 2020. Proceedings. Lecture Notes in Artificial Intelligence. Subseries of Lecture Notes in Computer Science (LNAI 12319), P636, DOI 10.1007/978-3-030-61377-8_45
[9] Pavan M.C, 2020, IEEE T AFFECT COMPUT, V1, DOI [10.1109/TAFFC.2020.3034050, DOI 10.1109/TAFFC.2020.3034050]
[10] Pedregosa F, 2011, J MACH LEARN RES, V12, P2825

← 1 2 →