Sentiment Analysis and Text Summarization

This solution was submitted to round 2 of Convolve, an ML/AI hackathon jointly organized by 6 IITs. The problem statement is about analysing the feedback from Cisco's Customer Support Team. Feedback is available for different job roles and we had to predict if each fedback is a positive or negative sentiment, followed by summarising the negative feedback for every job role.

data contains the training data test contains the test data convolve_epoch_2.ipynb is the notebook cn be run on Python3

Solution

• Sentiment Analysis using LSTMs
• Text Summarization using BART