Combating Online Hostile Posts in Regional Languages During Emergency Situation: First International Workshop, Constraint 2021, Collocated with AAAI 2

ISBN-13: 9783030736958 / Angielski / Miękka / 2021 / 258 str.

Tanmoy Chakraborty; Kai Shu; H. Russell Bernard

Spis treści

Identifying Offensive Content in Social Media Posts.- Identification and Classification of Textual Aggression in Social Media: Resource Creation and Evaluation.- Fighting an Infodemic: COVID-19 Fake News Dataset.- Revealing the Blackmarket Retweet Game: A Hybrid Approach.- Overview of CONSTRAINT 2021 Shared Tasks: Detecting English COVID-19 Fake News and Hindi Hostile Posts.- LaDiff ULMFiT: A Layer Differentiated training approach for ULMFiT.- Extracting latent information from datasets in The CONSTRAINT-2020 shared task on the hostile post detection.- Fake news and hostile posts detection using an ensemble learning model.- Transformer-based Language Model Fine-tuning Methods for COVID-19 Fake News Detection.- Tackling the infodemic : Analysis using Transformer based models.- Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English.- g2tmn at Constraint@AAAI2021: Exploiting CT-BERT and Ensembling Learning for COVID-19 Fake News Detection.- Model Generalization on COVID-19 Fake News Detection.- ECOL: Early Detection of COVID Lies Using Content, Prior Knowledge and Source Information.- Evaluating Deep Learning Approaches for Covid19 Fake News Detection.- A Heuristic-driven Ensemble Framework for COVID-19 Fake News Detection.- Identification of COVID-19 related Fake News via Neural Stacking.- Fake News Detection System using XLNet model with Topic Distributions: CONSTRAINT@AAAI2021 Shared Task.- Coarse and Fine-Grained Hostility Detection in Hindi Posts using Fine Tuned Multilingual Embeddings.- Hostility Detection in Hindi leveraging Pre-Trained Language Models.- Stacked embeddings and multiple fine-tuned XLM-RoBERTa models for Enhanced hostility identification.- Task Adaptive Pretraining of Transformers for Hostility Detection.- Divide and Conquer: An Ensemble Approach for Hostile Post Detection in Hindi.