Call for Participation: SemEval-2023 Shared Task 3 - Persuasion Techniques, Framing and Genre Detection in Online News in a Multi-lingual Setup
We are glad to invite you to participate in the SemEval-2023 Shared Task 3 on detecting the genre, the framing, and the persuasion techniques in online news.
The main drive behind this task is to foster development of methods and tools to support the analysis of online media content in order to understand what makes a text persuasive: which writing style is used, what key aspects are highlighted, and which persuasion techniques are used to influence the reader.
The data used for for this task is made of articles collected from 2020 to mid 2022, they revolve around a range of widely discussed topics such as COVID-19, climate change, abortion, migration, the Russo-Ukrainian war, and local elections.
The data presents several novelties: it is multilabel, multilingual (🇫🇷🇵🇱🇬🇧🇷🇺🇮🇹🇩🇪), uses an updated fine-grained taxonomy of persuasion techniques and covers complementary dimensions of what makes a text persuasive. The train contains currently more than 1600 documents and more than 40000 spans annotated for persuasion techniques!
Are you interested in using AI systems to analyse political speech, media bias or rhetoric? Then you should not miss this task!!!
URL
https://propaganda.math.unipd.it/semeval2023task3/
TASKS
We offer three subtasks on news articles in six languages (English, French, German, Italian, Polish, and Russian).
Subtask 1: NEWS GENRE CATEGORISATION
Given a news article, determine whether it is an opinion piece, aims at objective news reporting, or is a satire piece. This is a multi-class task at article-level.
Subtask 2: NEWS FRAME CATEGORISATION
Given a news article, identify the generic frames used in the article. This is a multi-class task at article-level.
Subtask 3: PERSUASION TECHNIQUE DETECTION
Given a news article, identify the persuasion techniques in each paragraph. This is a multi-label task at paragraph level.
PARTICIPATION & EVALUATION
The participants may take part in any number of subtask-language pairs (even just one), and may train their systems using the data for all languages (in a multilingual setup).
To promote the development of language-agnostic solutions, there will be also two "surprise" languages for which we will release only test data for evaluation purposes.
IMPORTANT DATES
23 September 2022: Registration opens 23 September 2022: Release of the first batch of the training\development set 12 January 2023: Release of the test set 22 January 2023: Test submission site closes February 2023: Paper Submission Deadline March 2023: Notification to authors April 2023: Camera ready papers due Summer 2023: SemEval 2023 workshop
TASK ORGANIZERS
Giovanni Da San Martino, Preslav Nakov, Jakub Piskorski, Nicolas Stefanovitch