Classify Customer Feedback
Given a dataset of customer feedback classified as Positive or Negative, build a deep neural network to classify feedback accurately. A review is categorized based on tone, words, length, and the style of writing by the customers.
Datasets
train.csv— data used to train the modeltest.csv— data used to test predictionssubmissions.csv— populate this file with the resultssample_submission.csv— sample reference of submission data file
Task
Submit the predictions on the test dataset using your optimized model.
For each record in the test set (test.csv), predict the value of the feedback variable.
You should submit a CSV file with a header row and one row per test entry.
The file submissions.csv should have exactly 2 columns:
customer_review— customer reviewfeedback— feedback (0-Negative, 1-Positive)
Build a neural network to classify customer feedback.
Experiment with different preprocessing methods, numbers of layers, types of layers, activation functions, and any other relevant parameters. Compile the model by specifying the loss function and optimizer. Ensure that the model is not overfitting.
Assess model performance on train.csv using the F1 Score metric. The model will be tested for robustness using a different dataset.
This BBC OA problem is a binary text classification task: predict whether each customer review is Negative (0) or Positive (1). A solid solution usually starts with text preprocessing, tokenization, and sequence padding, followed by a neural network such as Embedding + BiLSTM/GRU or a lightweight CNN-based classifier. Since the evaluation metric is F1 score, the model should be tuned for class balance and generalization rather than accuracy alone. Regularization techniques like dropout and early stopping, along with careful validation, are important to avoid overfitting and improve robustness on the hidden test set.
