Why does patient participation increase social performance for healthcare conferences?
Background: Healthcare conference participants use of social media, and Twitter in particular, have grown to become a significant part of the conference experience with 1,159,093 tweets for 2013. In our prior research analysis with data from 2013, we observed a recent trend to promote patient inclusive conferences. That analysis concluded that 65 out of 100 conferences were found to have one or more patients in its top 100 influencers by mentions. Those conferences with more patients were found to have a stronger social performance with higher average number of tweets, larger reach with a higher average number of participants and a more dynamic conversation with a higher average tweets per participant.
In this follow up study, we will analyze this social dataset to find reasons why patient inclusiveness has such a positive effect on conferences. By extending the analysis time-range to also include 2014 we will be able to identify the growth rate of this patient inclusiveness movement while also attempting to validate our first study.
Methods: For this study, we will start by first analyzing the data that Symplur has collected from 1,447 healthcare conferences that took place in 2014 worldwide. We will select those that have a minimum of 1,000 tweets during the conference. A random sampling of 100 conferences will help to scale down the data set. We will compute the top 100 influencers by mentions from each conference, and these 10,000 participants will be categorized and identified as either a patient or non-patient. From this we will group the 100 conferences into two segments - those with more patients and those with less patients. Comparison analysis can now be performed to both identify the growth trend of patient participation and validate the findings of our prior research study.
We will extend this study by analyzing and comparing two aggregate groups of participants and their tweets, those identified as patients and those identified as non-patients. From this comparison study we will look at average volume of tweets to answer which group fosters a larger conversation. We will analyze the differences in retweets to answer which group creates more engaging tweets. Finally, we will look at follower numbers and impressions to answer which group has a larger social audience, which may give light to why a conference’s social reach increase by including patients.
We also want to answer which group exhibits a more social behavior from analyzing the tweets and computing the mention rate, which identifies the more conversational group. Average number of unique participants they mention will answer which group includes more people in the conversations. Social network analysis will help us understand to what degree the two groups interact and which group is more likely to reach out to the other. To answer how these two groups talk differently, we will conduct a word frequency analysis of the tweet content. This may help us answer why one group’s tweets are more engaging and more widely circulated.