Description

- Words-level & Character-level news classifier

• Words-level news classifier
  • Input: word-level faeture from Word tokenizer
  • Conv1D-based-model
• Character-level news classifier
  • Input: character-level faeture from Character tokenizer
  • Conv1D-based-model

- Ensemble of two input feature spaces

• Concatenating two layer of each classifier and FC

Contents

- Train & Evaluate Ensemble News Classifier of Words-level & Character-level

• Analysis of News Aggregator Dataset
• Two level language preproecessing
• Single classifier of two level
• Ensemble two single classifier
• Train & Evaluation: optimization, ROC curve, Confusion matrix etc.

Datasets

- News Aggregater

https://www.kaggle.com/uciml/news-aggregator-dataset

Author

- LinkedIn: https://www.linkedin.com/in/taeyong-kong-016bb2154

- Blog URL: https://blog.naver.com/qbxlvnf11

- Email: qbxlvnf11@google.com, qbxlvnf11@naver.com