SemEval 2019 Task 4 Hyperpartisan

• Competition Details: https://pan.webis.de/semeval19/semeval19-web/

Data

• Sample data is in ./data/

Steps:

• Use Keras to build a RNN or LSTM, understand how to process input data. Link
• Text Classification Using CNN, LSTM and Pre-trained Glove Word Embeddings Part1 Part3
• Hyperparemeters setting: sequence length, size of word vocabulary, learning rate, number of batch etc.
• Pytoch implement RNN and LSTM. Morvan pytorch, Pytorch RNN, Pytorch LSTM
• Pytoch implement CNN CNN
• Model optimization
• Visulization

Related References:

• Beyond Binary Labels: Political Ideology Prediction of Twitter Users
• A Stylometric Inquiry into Hyperpartisan and Fake News
• Classification of Moral Foundations in Microblog Political Discourse
• Convolutional Neural Networks for Sentence Classification
• Fake News Detection on Social Media: A Data Mining Perspective
• Satirical News Detection and Analysis using Attention Mechanism and Linguistic Features
• Recurrent Convolutional Neural Networks for Text Classification
• A STRUCTURED SELF-ATTENTIVE SENTENCE EMBEDDING
• Attention is All you Need
• A Convolutional Attention Model for Text Classification
• Attention-based LSTM for Aspect-level Sentiment Classification
• Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning
• Attention? Attention!

Citation:

@inproceedings{zhang2019ubc,
  title={UBC-NLP at SemEval-2019 Task 4: Hyperpartisan News Detection With Attention-Based Bi-LSTMs},
  author={Zhang, Chiyu and Rajendran, Arun and Abdul-Mageed, Muhammad},
  booktitle={Proceedings of the 13th International Workshop on Semantic Evaluation},
  pages={1072--1077},
  year={2019}
}