This is submitted to Bright Data Web Scraping Challenge: The most creative use of network data in artificial intelligence models
what i built
The “Course Recommendation Sentiment Analysis” project leverages web scraping and powerful machine learning models, featuring a random forest classifier trained on the Coursera dataset, to evaluate courses based on user reviews and sentiment, providing a more than traditional star rating. A more detailed rating system. Users simply enter the URL of the course they want to evaluate, and the system extracts the reviews and categorizes them as positive, negative, or neutral. The resulting course ratings are calculated based on these sentiments, helping potential learners make informed decisions. Additionally, the app offers a course comparison feature that allows users to evaluate courses based on different criteria. This innovative approach, built using Python, Flask, and the YouTube API, empowers individuals to make educational choices tailored to their specific needs and preferences, thereby enhancing the online learning experience.
demonstration
https://res.cloudinary.com/dpwustwce/image/upload/v1734845594/qjlclhnfikf3lja9qk6t.gif
How I use Bright Data
Collect instant user reviews and reviews from course platforms like Coursera. Preprocess the data to remove noise, label sentiment (positive, negative, neutral) and build it into a training-ready format. Fine-tune sentiment analysis models (such as Random Forest or Transformer-based models) and integrate them into Flask-based applications for personalized course recommendations and comparisons.