Analysis of Public Perceptions about Ebola to Inform Helath Information Messages: Content and Trend Analysis of Tweets

Background:  Health information needs must be adequately assessed for effective communication with the public during outbreaks like Ebola.  Twitter can be used to effectively address these challenges.  Our study demonstrates the use of Twitter as a real-time method of Ebola outbreak surveillance to examine content of public knowledge and attitudes.

 Methods:  Twitter user communication about the current Ebola epidemic was examined through content and trend analysis to capture public perceptions of Ebola. We employed a Natural Language Processing approach in the analysis of Ebola tweet content.  Ebola-related keywords included #Ebola, #EbolaOutbreak, #EbolaVirus, #EbolaFacts and Ebola. 

 Results: A total of 42,236 tweets (16,499 unique, 25,737 retweet) mentioning Ebola were posted and disseminated to 9,362,267,048 people.  Data elements collected for tweets included contents, time stamps, message type (unique or retweet), and followers (number of disseminated).  Public attitudes were captured through trend analysis, revealing communication stimulated by public concern, mirroring news alerts. Tweets happened around health advisories, case identification, and the US return of infected workers.  Four main public topics of concern were discussed in tweet content: 1) Risk Factors; 2) Prevention Education; 3) Disease Trends and 4) Compassion. 

 Conclusion:  Our results provide insight into public perceptions, and how Titter can be used to evaluate prevention education efforts and inform data information messages for widespread dissemination.   Our study revealed the critical need for effective health education messages to accompany news alerts regarding Ebola.  Our findings also demonstrate the usefulness of Twitter mining to inform public health education.