@inproceedings{bangerter-etal-2023-unisa,
title = "Unisa at {S}em{E}val-2023 Task 3: A {SHAP}-based method for Propaganda Detection",
author = "Bangerter, Micaela and
Fenza, Giuseppe and
Gallo, Mariacristina and
Loia, Vincenzo and
Volpe, Alberto and
Maio, Carmen De and
Stanzione, Claudio",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.122",
doi = "10.18653/v1/2023.semeval-1.122",
pages = "885--891",
abstract = "This paper presents proposed solutions for addressing two subtasks in SemEval-2023 Task 3: {``}Detecting the Genre, the Framing, and the Persuasion techniques in online news in a multi-lingual setup. In subtask 1, {``}News Genre Categorisation, the goal is to classify a news article as an opinion, a report, or a satire. In subtask 3, {``}Detection of Persuasion Technique, the system must reveal persuasion techniques used in each news article paragraph choosing among23 defined methods. Solutions leverage the application of the eXplainable Artificial Intelligence (XAI) method, Shapley Additive Explanations (SHAP). In subtask 1, SHAP was used to understand what was driving the model to fail so that it could be improved accordingly. In contrast, in subtask 3, a re-calibration of the Attention Mechanism was realized by extracting critical tokens for each persuasion technique. The underlying idea is the exploitation of XAI for countering the overfitting of the resulting model and attempting to improve the performance when there are few samples in the training data. The achieved performance on English for subtask 1 ranked 6th with an F1-score of 58.6{\%} (despite 78.4{\%} of the 1st) and for subtask 3 ranked 12th with a micro-averaged F1-score of 29.8{\%} (despite 37.6{\%} of the 1st).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bangerter-etal-2023-unisa">
<titleInfo>
<title>Unisa at SemEval-2023 Task 3: A SHAP-based method for Propaganda Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Micaela</namePart>
<namePart type="family">Bangerter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Fenza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariacristina</namePart>
<namePart type="family">Gallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincenzo</namePart>
<namePart type="family">Loia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Volpe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carmen</namePart>
<namePart type="given">De</namePart>
<namePart type="family">Maio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudio</namePart>
<namePart type="family">Stanzione</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents proposed solutions for addressing two subtasks in SemEval-2023 Task 3: “Detecting the Genre, the Framing, and the Persuasion techniques in online news in a multi-lingual setup. In subtask 1, “News Genre Categorisation, the goal is to classify a news article as an opinion, a report, or a satire. In subtask 3, “Detection of Persuasion Technique, the system must reveal persuasion techniques used in each news article paragraph choosing among23 defined methods. Solutions leverage the application of the eXplainable Artificial Intelligence (XAI) method, Shapley Additive Explanations (SHAP). In subtask 1, SHAP was used to understand what was driving the model to fail so that it could be improved accordingly. In contrast, in subtask 3, a re-calibration of the Attention Mechanism was realized by extracting critical tokens for each persuasion technique. The underlying idea is the exploitation of XAI for countering the overfitting of the resulting model and attempting to improve the performance when there are few samples in the training data. The achieved performance on English for subtask 1 ranked 6th with an F1-score of 58.6% (despite 78.4% of the 1st) and for subtask 3 ranked 12th with a micro-averaged F1-score of 29.8% (despite 37.6% of the 1st).</abstract>
<identifier type="citekey">bangerter-etal-2023-unisa</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.122</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.122</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>885</start>
<end>891</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unisa at SemEval-2023 Task 3: A SHAP-based method for Propaganda Detection
%A Bangerter, Micaela
%A Fenza, Giuseppe
%A Gallo, Mariacristina
%A Loia, Vincenzo
%A Volpe, Alberto
%A Maio, Carmen De
%A Stanzione, Claudio
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F bangerter-etal-2023-unisa
%X This paper presents proposed solutions for addressing two subtasks in SemEval-2023 Task 3: “Detecting the Genre, the Framing, and the Persuasion techniques in online news in a multi-lingual setup. In subtask 1, “News Genre Categorisation, the goal is to classify a news article as an opinion, a report, or a satire. In subtask 3, “Detection of Persuasion Technique, the system must reveal persuasion techniques used in each news article paragraph choosing among23 defined methods. Solutions leverage the application of the eXplainable Artificial Intelligence (XAI) method, Shapley Additive Explanations (SHAP). In subtask 1, SHAP was used to understand what was driving the model to fail so that it could be improved accordingly. In contrast, in subtask 3, a re-calibration of the Attention Mechanism was realized by extracting critical tokens for each persuasion technique. The underlying idea is the exploitation of XAI for countering the overfitting of the resulting model and attempting to improve the performance when there are few samples in the training data. The achieved performance on English for subtask 1 ranked 6th with an F1-score of 58.6% (despite 78.4% of the 1st) and for subtask 3 ranked 12th with a micro-averaged F1-score of 29.8% (despite 37.6% of the 1st).
%R 10.18653/v1/2023.semeval-1.122
%U https://aclanthology.org/2023.semeval-1.122
%U https://doi.org/10.18653/v1/2023.semeval-1.122
%P 885-891
Markdown (Informal)
[Unisa at SemEval-2023 Task 3: A SHAP-based method for Propaganda Detection](https://aclanthology.org/2023.semeval-1.122) (Bangerter et al., SemEval 2023)
ACL
- Micaela Bangerter, Giuseppe Fenza, Mariacristina Gallo, Vincenzo Loia, Alberto Volpe, Carmen De Maio, and Claudio Stanzione. 2023. Unisa at SemEval-2023 Task 3: A SHAP-based method for Propaganda Detection. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 885–891, Toronto, Canada. Association for Computational Linguistics.