14th meeting of Forum for Information Retrieval Evaluation HASOC-2022 Shared task on HATE AND OFFENSIVE CONTENT IDENTIFICATION FIRE-22 9th to 13th Dec 2022 in a Hybrid mode at Kolkata, India
Call for Shared Task Participation https://hasocfire.github.iohttps://url6.mailanyone.net/scanner?m=1oIuaZ-000ArL-3w&d=3%7Cmail%2F14%2F1659456600%2F1oIuaZ-000ArL-3w%7Cin6a%7C57e1b682%7C10977208%7C9441127%7C62E94E2B4DE769E70749E4B079F530DD&s=Xd9ZBqtzeg6-uKmmReddKOc2MJU&o=https%3A%2F%2Fhasocfire.github.io%2F
Task description: This task aims to study the various forms of problematic content, such as aggressiveness, hate, offensive, and abusive content in conversational dialogue (with context) on online platforms, such as Twitter. Systems should use the context of a conversation in order to identify problematic content.
Task 1: ICHCL contextual binary classification (Hinglish and German) This task focused on the binary classification (Subtask-1) of such conversational tweets with tree-structured data into: (NOT) Non-Hate-Offensive - This tweet, comment, or reply does not contain any Hate speech, or profane, offensive content. (HOF) Hate and Offensive - This tweet, comment, or reply contains Hate, offensive, and profane content in itself or supports hate expressed in the parent tweet.
The data set will be offered in Code Mixed Hindi English as well as in German.
Task 2: ICHCL contextual multiclass classification Furthermore, for Hinglish (Code Mixed Hindi English), we're introducing a multiclass task that further divides the HOF tweets into 2 subclasses so this task will contain 3 labels: (SHOF) Standalone Hate - This tweet, comment, or reply contains Hate, offensive, and profane content in itself. (CHOF) Contextual Hate - Comment or reply is supporting the hate, offence and profanity expressed by its parent. This includes affirming the hate with positive sentiment and having apparent hate. (NOT) Non-Hate-Offensive - This tweet, comment, or reply does not contain any Hate speech, or profane, offensive content.
For more information on task-1 and 2 please visit: https://hasocfire.github.io/hasoc/2022/ichcl.htmlhttps://url6.mailanyone.net/scanner?m=1oIuaZ-000ArL-3w&d=3%7Cmail%2F14%2F1659456600%2F1oIuaZ-000ArL-3w%7Cin6a%7C57e1b682%7C10977208%7C9441127%7C62E94E2B4DE769E70749E4B079F530DD&s=mVcuyw4IhVNE0xeY-aSFYUis1PE&o=https%3A%2F%2Fhasocfire.github.io%2Fhasoc%2F2022%2Fichcl.html
Task 3: Offensive Language Identification in Marathi This task aims to evaluate the hierarchical modelling of offensive language identification in Marathi. The task has three subtasks.
Subtask-1: Offensive Language Detection In this subtask, the goal is to discriminate between offensive and non-offensive posts. Offensive posts include insults, threats, and posts containing any form of untargeted profanity. Each instance is assigned one of the following two labels: OFF - Posts containing any form of non-acceptable language (profanity) or a targeted offence, which can be veiled or direct. NOT - Posts that do not contain offence or profanity.
Subtask-2: Categorisation of Offensive Language In subtask B, the goal is to predict the type of offence. Only posts labelled as Offensive (OFF) in subtask A are included in subtask B. The two categories in subtask B are the following: Targeted Insult (TIN): Posts containing an insult/threat to an individual, group, or others. Untargeted (UNT): Posts containing non-targeted profanity and swearing. Subtask-3: Offense Target Identification Subtask C focuses on the target of offences. Only posts that are either insults or threats (TIN) are considered in this third layer of annotation. The three labels in subtask C are the following: Individual (IND): Posts targeting an individual. Group (GRP): The target of these offensive posts is a group of people considered to a unity due to the same ethnicity, gender or sexual orientation, political affiliation, religious belief, or other common characteristics. Other (OTH): The target of these offensive posts does not belong to any of the previous two categories.
Timeline: 5th June Task Announcement, Data of HASOC 2019,20,21 Available 1st Aug Training Data Release 1st Sept Test Data Release and Run Submission Starts 3rd Sept Registration Deadline 8th Sept Deadline for run submission 10nd Sept Result Declaration 30th Sept Paper Submission Deadline 10th Oct Review Distribution 20th Oct Revised system description paper submission 9th-13 Dec FIRE takes place in Hybrid mode
Organizers: Thomas Mandl - University of Hildesheim, Germany Sandip Modha - LDRP-ITR, Gandhinagar, India Prasenjit majumder - DA-IICT, Gandhinagar, India Shrey Satapara - Indian Institute of Technology, Hyderabad, India Hiren Madhu - Indian Institute of Science, Banglore, India Tharindu Ranasinghe - University of Wolverhampton, UK Marcos Zampieri - Rochester Institute of Technology, USA Kai North - Rochester Institute of Technology, USA Damith Premasiri - University of Wolverhampton, UK
For more information, please visit: https://hasocfire.github.io/hasoc/2022/index.htmlhttps://url6.mailanyone.net/scanner?m=1oIuaZ-000ArL-3w&d=3%7Cmail%2F14%2F1659456600%2F1oIuaZ-000ArL-3w%7Cin6a%7C57e1b682%7C10977208%7C9441127%7C62E94E2B4DE769E70749E4B079F530DD&s=i1wiT6rzyopso21srwbJX37gHS0&o=https%3A%2F%2Fhasocfire.github.io%2Fhasoc%2F2022%2Findex.html For participation please visit: https://hasocfire.github.io/hasoc/2022/registration.htmlhttps://url6.mailanyone.net/scanner?m=1oIuaZ-000ArL-3w&d=3%7Cmail%2F14%2F1659456600%2F1oIuaZ-000ArL-3w%7Cin6a%7C57e1b682%7C10977208%7C9441127%7C62E94E2B4DE769E70749E4B079F530DD&s=bai0k06gptWOEth_bhhrvABwVZ4&o=https%3A%2F%2Fhasocfire.github.io%2Fhasoc%2F2022%2Fregistration.html
For any clarification please contact us at hasocfire@gmail.commailto:hasocfire@gmail.com
Looking forward to your participation