Hashtags in Plastic Surgery: A Sentiment Analysis of over 1 Million Tweets.

ABSTRACT

BACKGROUND: Current literature has sparse recommendations that guide social networking practices in plastic surgery. To address this, we used natural language processing and sentiment analysis to investigate the differences in plastic surgery-related terms and hashtags on Twitter. METHODS: Over 1 million tweets containing keywords #plasticsurgery, #cosmeticsurgery, and their non-hashtagged versions plastic surgery and cosmetic surgery were collected from the Twitter Gardenhose feed spanning from 2012 to 2016. We extracted the average happiness/positivity (h-avg) using hedonometrics and created word-shift graphs to determine influential words. RESULTS: The most popular keywords were plastic and cosmetic surgery, comprising more than 90% of the sample. The positivity scores for plastic surgery, cosmetic surgery, #plasticsurgery, and #cosmeticsurgery were 5.72, 6.00, 6.17, and 6.18, respectively. Compared to plastic surgery, the term cosmetic surgery was more positive because it lacked antagonistic words, such as "fake," "ugly," "bad," "fails," and "wrong." For similar reasons, #plasticsurgery and #cosmeticsurgery were more positively associated than their non-hashtagged counterparts. CONCLUSION: Plastic surgery-related hashtags are more positively associated than their non-hashtagged versions. The language associated with such hashtags suggests a different user profile than the public and, given their underutilization, remain viable channels for professionals to achieve their diverse social media goals. LEVEL OF EVIDENCE V This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .