Stance classification in tweets using Recurrent Neural Networks
Stance classification is a subcategory of opinion mining where the task is to automatically determine whether the author of a piece of text is in favor or against a given target. It can be formulated in different ways. In our context, we define stance detection to mean automatically determining from the text whether the author is in favor or against of the given target, or whether neither inference is likely.
In this project, we have implemented a Deep Learning technique to automatically detect the stance of a particular tweet, when the tweet statement and target of that tweet is provided. The data taken from SemEval – 2016 (Task 6 Subtask A) competition. The source of a data is “Semeval-2016 Task 6: Detecting Stance in Tweets.
The main aim of our project is to build a deep learning model to classify the type of stance from tweets that are associated with one of five politically-charged targets: “Atheism”, “the Feminist Movement”, “Climate Change is a Real Concern”, “Legalization of Abortion” and “Hillary Clinton”.
The Final code of developed model and approach is present in file "S375155_S3779009.ipynb". The detail report of this task is present in file "S375155_S3779009_REPORT.pdf"