Text Mining in Healthcare

This giant pharmaceutical firm was looking for customer feedback. It wanted to know what people liked about its products. Did people prefer the company‘s product over other products? Did these preferences develop and change over time? In addition, the company was legally required to report any adverse product reactions, so a connection to customers was doubly important.

This firm focused on collecting publicly available information with RapidMiner, primarily from the diabetic community, specialized diabetes forums, blogs and the major social networks. The information was in the form of millions of individual texts and posts per year, far more than could be reviewed by human eyes. Is this text about the company’s product? Is it about a competitor’s product? Is the post about the consumer’s desires about the product or is it from real experience? Once the appropriate texts were identified, RapidMiner’s sentiment analysis tools were used to determine whether each one was positive or negative.