Collecting and Analyzing Patient Experiences of Health Care From Social Media

Abstract

Background: Social Media, such as Yelp, provides rich information of consumer experience. Previous studies suggest that Yelp can serve as a new source to study patient experience. However, the lack of a corpus of patient reviews causes a major bottleneck for applying computational techniques.

Objective: The objective of this study is to create a corpus of patient experience (COPE) and report descriptive statistics to characterize COPE.

Methods: Yelp reviews about health care-related businesses were extracted from the Yelp Academic Dataset. Natural language processing (NLP) tools were used to split reviews into sentences, extract noun phrases and adjectives from each sentence, and generate parse trees and dependency trees for each sentence. Sentiment analysis techniques and Hadoop were used to calculate a sentiment score of each sentence and for parallel processing, respectively.

Results: COPE contains 79,173 sentences from 6914 patient reviews of 985 health care facilities near 30 universities in the United States. We found that patients wrote longer reviews when they rated the facility poorly (1 or 2 stars). We demonstrated that the computed sentiment scores correlated well with consumer-generated ratings. A consumer vocabulary to describe their health care experience was constructed by a statistical analysis of word counts and co-occurrences in COPE.

Conclusions: A corpus called COPE was built as an initial step to utilize social media to understand patient experiences at health care facilities. The corpus is available to download and COPE can be used in future studies to extract knowledge of patients' experiences from their perspectives. Such information can subsequently inform and provide opportunity to improve the quality of health care.

Keywords: consumer health information; health care; natural language processing; patient satisfaction; social media.

Figure 1

Part-of-speech analysis conducted on each sentence in COPE.

Figure 2

Number of reviews per years.

Figure 3

Distribution of reviews.

Figure 4

Distribution of review length.

Figure 5

Number of sentences per review.

Figure 6

Distribution of the rating scores per review.

Figure 7

Length of review versus rating score.

Figure 8

Distribution of the sentiment score per sentence.

Figure 9

Mean sentiment score of sentences in each review per patient-generated overall rating.

Figure 10

Sentiment score per length of sentence.

Figure 11

Cumulative usage of terms versus rank of terms.

Figure 12

A network of words used by customers to describe their experiences. The size of the node indicates the frequency of the word and the width of the lines indicates the number of co-occurrences of the word-pair in the same review. An example of usage of the word “platelet” is shown in the call-out box.