Sentence-Level Propaganda Detection in News Articles with Transfer Learning and BERT-BiLSTM-Capsule Model

Abstract

In recent years, the need for communication increased in online social media. Propaganda is a mechanism which was used throughout history to influence public opinion and it is gaining a new dimension with the rising interest of online social media. This paper presents our submission to NLP4IF-2019 Shared Task SLC: Sentence-level Propaganda Detection in news articles. The challenge of this task is to build a robust binary classifier able to provide corresponding propaganda labels, propaganda or non-propaganda. Our model relies on a unified neural network, which consists of several deep leaning modules, namely BERT, BiLSTM and Capsule, to solve the sentencelevel propaganda classification problem. In addition, we take a pre-training approach on a somewhat similar task (i.e., emotion classification) improving results against the coldstart model. Among the 26 participant teams in the NLP4IF-2019 Task SLC, our solution ranked 12th with an F 1-score 0.5868 on the official test data. Our proposed solution indicates promising results since our system significantly exceeds the baseline approach of the task organizers by 0.1521 and is slightly lower than the winning system by 0.0454.

Inno at SemEval-2020 Task 11: Leveraging Pure Transfomer for Multi-Class Propaganda Detection

“…Almost all teams used some Transformer-based models (especially BERT (Devlin et al, 2018)) either to get embeddings or as a pretrained model (Yoosuf and Yang, 2019) (Hou and Chen, 2019). Other teams often used ensembles with different features and models inside: LSTM-CRF (Gupta et al, 2019), XGBoost (Tayyar Madabushi et al, 2019), BiLSTM (Vlad et al, 2019) Figure 1: Class distribution in the train data, where A is "Loaded Language", B is "Name Calling or Labeling", C is "Repetition", D is "Doubt", E is "Exaggeration or Minimisation", and F represents all the remaining 9 classes.…”

Findings of the NLP4IF-2019 Shared Task on Fine-Grained Propaganda Detection

“…Team Mindcoders (Vlad et al, 2019) combined BERT, Bi-LSTM and Capsule networks (Sabour et al, 2017) into a single deep neural network and pre-trained the resulting network on corpora used for related tasks, e.g., emotion classification.…”

Implementation of the BERT-derived architectures to tackle disinformation challenges

“…For example, [30] describes the detection of government propaganda, [15] focuses on analyzing the title's compliance with the contents of the text, and [27] conducts teaching on relatively small data to distinguish between fake news and satire. Attempts to combat fake news using machine learning and artificial intelligence techniques were also undertaken in other works using methods based on deep neural networks, on RNN recursive networks, or using traditional learnings algorithms like: RF (random forest), LR (logistic regression), NB (naive Bayes), MLP (multilayer perceptron) or support vector machine (SVM).…”