natural-language-processing

Propaganda detection

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in propaganda-detection

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find propaganda-detection models and implementations

Datasets

Analysing state-backed propaganda websites: a new dataset and linguistic study

Subtasks

Propaganda span identification Propaganda technique identification

Most implemented papers

Semi-supervised Stance Detection of Tweets Via Distant Network Supervision

Tanmoy Chakraborty, Soumen Chakrabarti, Subhabrata Dutta, Samiya Caur•Sun Jan 02 2022

This work presents SANDS, a new semi-supervised stance detector that starts from very few labeled tweets, and achieves a macro-F1 score of 0.55 (0.49) on US (India)-based datasets, outperforming 17 baselines substantially, particularly for minority stance labels and noisy text.

16

Content

0

Paper Graph

Towards Detection of Subjective Bias using Contextualized Word Embeddings

Kartikey Pant, R. Mamidi, Tanvi Dadu•Sat Feb 15 2020

This work performs comprehensive experiments for detecting subjective bias using BERT-based models on the Wiki Neutrality Corpus (WNC), and proposes BERT -based ensembles that outperform state-of-the-art methods like BERTlarge by a margin of 5.6 F1 score.

25 0

Paper Graph

Large Language Models for Propaganda Detection

Kilian Sprenkamp, Daniel Gordon Jones, Liudmila Zavolokina•Mon Oct 09 2023

This study analyzes the potential and challenges of LLMs in complex tasks like propaganda detection, and demonstrates that GPT-4 achieves comparable results to the current state-of-the-art approach using RoBERTa.

17 0

Paper Graph

Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data

H. T. Madabushi, E. Kochkina, Michael Castelle•Sun Mar 15 2020

It is shown that BERT, while capable of handling imbalanced classes with no additional data augmentation, does not generalise well when the training and test data are sufficiently dissimilar, and how to address this problem by providing a statistical measure of similarity between datasets and a method of incorporating cost-weighting into BERT when theTraining and test sets are dissimilar.

117 0

Paper Graph

UTMN at SemEval-2020 Task 11: A Kitchen Solution to Automatic Propaganda Detection

Anna Glazkova, Elena Mikhalkova, Nadezhda Ganzherli, Yuliya Bidulya•Fri Aug 21 2020

A fast solution to propaganda detection at SemEval-2020 Task 11, based on feature adjustment, using per-token vectorization of features and a simple Logistic Regression classifier to quickly test different hypotheses about the data.

5 0

Paper Graph

Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China

Rong-Ching Chang, Chun-Ming Lai, Kai-Lai Chang, Chu-Hsing Lin•Sun Jun 13 2021

This research aims to bridge the information gap by providing a multi-labeled propaganda techniques dataset in Mandarin based on a state-backed information operation dataset provided by Twitter, and applies aMulti-label text classification using fine-tuned BERT.

14 0

Paper Graph

YNU-HPCC at SemEval-2020 Task 11: LSTM Network for Detection of Propaganda Techniques in News Articles

Jiaxu Dao, Jin Wang, Xuejie Zhang•Sun Aug 23 2020

The GloVe word representation, the BERT pretraining model, and the LSTM model architecture are implemented to accomplish propaganda detection techniques for news articles in the SemEval-2020 task 11, which significantly outperforms the officially released baseline method.

7 0

Paper Graph

ProtoTEx: Explaining Model Decisions with Prototype Tensors

J. Li, Anubrata Das, Chitrank Gupta, Venelin Kovatchev, Matthew Lease•Sun Apr 10 2022

A user study shows that prototype-based explanations help non-experts to better recognize propaganda in online news and a novel interleaved training algorithm that effectively handles classes characterized by ProtoTEx indicative features.

32 0

Paper Graph

CyberWallE at SemEval-2020 Task 11: An Analysis of Feature Engineering for Ensemble Models for Propaganda Detection

Verena Blaschke, Maxim Korniyenko, Sam Tureski•Fri Aug 21 2020

This paper uses a bi-LSTM architecture in the SI subtask and train a complex ensemble model for the TC subtask, built using embeddings from BERT in combination with additional lexical features and extensive label post-processing.

7 0

Paper Graph

IITD at WANLP 2022 Shared Task: Multilingual Multi-Granularity Network for Propaganda Detection

Preslav Nakov, Shubham Mittal•Sun Oct 30 2022

The experimental results and analysis show that it does not help to use a much larger English corpus annotated with propaganda techniques, regardless of whether used in English or after translation to Arabic.

7 0

Paper Graph

Adding a benchmark result helps the community track progress.