The objective of this project is to develop a Drug Recommendation System that leverages sentiment analysis of drug reviews to provide personalized recommendations. This system aims to help users find suitable drugs based on the experiences and feedback of other users with similar conditions. The project involves data collection, preprocessing, sentiment analysis, recommendation generation, and deployment using Flask.
This Project is based on sentiment analysis of the drug whether the drug should be given for patients, it is advisable or not to the patients. This project is implemented using Natural Language processing using a bag of words model and other techniques like vectorization to analyze the drug reviews
Data Collection
Objective
The first step involves gathering a comprehensive dataset containing drug reviews to analyze user sentiments and derive recommendations.
Sources
- Online Platforms: Websites such as Drugs.com and user forums and Kaggle .
- Existing Datasets: Publicly available datasets like the UCI Drug Review dataset.
Content
The dataset should include:
- Review Text: The content of the user's review.
- Drug Name: The name of the drug being reviewed.
- Condition: The medical condition the drug is intended to treat.
- User Ratings: Numerical ratings provided by the users.
- Metadata: Additional information such as review date, user demographics, etc.
Methods
Collaborative Filtering
- Leverage user reviews and ratings to find similar users and recommend drugs.
Content-Based Filtering
- Recommend drugs similar to those the user has positively reviewed based on drug features and user preferences.
Hybrid Approaches
- Combine collaborative and content-based methods for more accurate recommendations.
Installation Steps :-
- Install Python 3.7
- Install all dependencies cmd -python -m pip install --user -r requirements.txt
- Finally run cmd - python app.py