Use a machine learning model to detect fake news and categorize news articles into 4 categories: {'agree', 'disagree', 'unrelated', 'discuss'}
Input
A headline and a body text - either from the same news article or from two different articles.
Output
Classify the stance of the body text relative to the claim made in the headline into one of four categories:
- Agrees: The body text agrees with the headline.
- Disagrees: The body text disagrees with the headline.
- Discusses: The body text discuss the same topic as the headline, but does not take a position
- Unrelated: The body text discusses a different topic than the headline
The distribution of Stance classes in train_stances.csv is as follows:
| rows | unrelated | discuss | agree | disagree |
|---|---|---|---|---|
| 49972 | 0.73131 | 0.17828 | 0.0736012 | 0.0168094 |
Deep Neural Network: 86%
- find a suitable ML library for price prediction - Azure Machine Learning Library
- determine input features - (headline, body)
- find data to train the model - found
- build Azure experiment - done
- analyze model prediction accuracy - done
- design backend API
- design chatbot interface (possible integration with Slack?)
- test
- MS Azure ML library
- knowledge based data analysis
- speech recognition
- internationalization (optional)
- MS Bot Framework
- Stdlib backend API