Artificial Intelligence


Sentiment Classification Over Brazilian Supreme Court Decisions Using Multi-Channel CNN

Authors: Marcus Oliveira da Silva

Sentiment analysis seeks to identify the viewpoint(s) underlying a text document; In this paper, we present the use of a multichannel convolutional neural network which, in effect, creates a model that reads text with different n-gram sizes, to predict with good accuracy sentiments behind the decisions issued by the Brazilian Supreme Court, even with a very imbalanced dataset we show that a simple multichannel CNN with little to zero hyperparameter tuning and word vectors, tuned on network training, achieves excellent results on the Brazilian Supreme Court data. We report results of 97% accuracy and 84% average F1- score in predicting multiclass sentiment dimensions. We also compared the results with classical classification machine learning models like Naive Bayes and SVM.

Comments: 11 Pages.

Download: PDF

Submission history

[v1] 2019-10-27 18:08:55

Unique-IP document downloads: 104 times is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus