π΅οΈ Introduction
We all refer to reviews and ratings for movies & shows, either on IMDB or through our friends before we binge them. In this assignment, youβre tasked with identifying the rating of a review using sentiment analysis.
The training dataset consists of {sentence id, review, rating}. Given a review, your neural network should be able to assign a rating score between 1
to 5
- low to high, respectively.
Do note:
- Perform sentiment analysis using a neural network with just one input and output layer (with softmax as activation function).
- Youβre not allowed to have hidden layers.
- You will be working in & making submission through a notebook. You can follow the instructions in the starter code. You have to use it to train, predict & submit.
πΎ Dataset
The dataset contains training data and test data. You can find it under Resources.
π Files
train.csv
- (50000
samples) This file contains training data with sentence ids, reviews & corresponding ratings (1
to5
).test.csv
- (10000
samples) This file contains test data with sentence ids & reviews.
π Submission
Submissions will be made through the notebook following the instructions in the starter code.
π Evaluation Criteria
The evaluation will be done according to the following criterion:
- F1 score (Harmonic Mean of precision & recall)
π± Contact
- DL for NLP TAs