Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
I have a some experience from Uni with convolutional NN and edge detection, but haven't much explored the other types of machine learning models.
I was wondering if there might be one that is suited for being able to use certain, textual keywords (for example, words that were parsed from internet news sources) in order to arrive at some binary, yes/no decision?
The most obvious binary classification task coming from text data is sentiment analysis. Kaggle is plenty of datasets such as this one on movie reviews.
Sentiment classifiers can be either very simple, like logistic regressions on naive Bayes classifiers, or very complex such as the ones based on RNNs and/or part-of-speech tagging models.
If you are interested in news specifically, similar models can be used to estimate news polarization.
