WebMD-Drug-Reviews-Dataset
OpenML dataset with id 43683
No author found.
Full work available at URL: https://api.openml.org/data/v1/download/22102508/WebMD-Drug-Reviews-Dataset.arff
Upload date: 24 March 2022
Dataset Characteristics
Number of features: 11 (numeric: 4, symbolic: 0 and in total binary: 0 )
Number of instances: 362,806
Number of instances with missing values: 42
Number of missing values: 42
Context
The dataset provides user reviews on specific drugs along with related conditions, side effects, age, sex, and ratings reflecting overall patient satisfaction.
Content
Data was acquired by scraping WebMD site. There are around 0.36 million rows of unique reviews and is updated till Mar 2020.
Inspiration
This dataset intended to answer following questions:
I. Identifying the condition of the patient based on drug reviews?
II. How to predict drug rating based on patients reviews?
III. How to visualize drug rating, kind of drugs, types of conditions a patient can have, sentiments based on reviews
