This project implements sentiment analysis on feedback collected from students regarding courses and faculty. The primary objective is to classify the feedback into distinct sentiment categories, providing valuable insights that can enhance the overall academic experience.
The feedback data is processed using Count Vectorization to convert text into numerical features. This method captures the frequency of words in the feedback, allowing for effective representation of the textual data. Several classification algorithms, including Naive Bayes, K-Nearest Neighbors (KNN), and Artificial Neural Networks (ANN), are applied to classify the sentiment of each feedback entry.
- Preprocess the Feedback Data: Utilize Count Vectorization to convert textual feedback into a numerical format.
- Apply Classification Models: Implement various machine learning models (Naive Bayes, KNN, ANN) to categorize the sentiment of the processed feedback.
Future efforts will focus on experimenting with additional classification algorithms and refining preprocessing techniques. The goal is to compare the effectiveness of different models in accurately classifying feedback sentiment and to enhance the overall performance of the sentiment analysis framework.
This project is licensed under the MIT License.