LAUSR

OBJECTIVES This study investigates the public's opinions on a new school meals policy for childhood obesity prevention, discovers aspects concerning those opinions, and identifies possible gender and regional differences in the U.S. METHODS We collected 14,317 relevant tweets from 11,715 users since the national policy enactment on Feb 9, 2010 through Dec 31, 2015. We applied opinion mining techniques to classify tweets into positive, negative, and neutral categories, and conducted content analysis to gain insights into aspects of opinions in terms of target, holder, source, and function. RESULTS There were more negative tweets about the school meals policy than positive ones (16.8% vs. 12.9%), in addition to neutral tweets (70.3%). The main targets for negative opinions were campaign and food, and those for positive opinions were policy and health benefits. The opinion holders represent a wide range of policy stakeholders. The first-hand source dominated the opinions. Statement accounted for the function of most opinions. Females (62.5%) were more involved than males (37.5%), and people in the South and the West regions (64.2%) engaged themselves more than people in the Northeast and the Midwest (35.8%) of the U.S. CONCLUSIONS Negative opinions about the school meals policy consistently outnumbered positive ones. The findings discovered the public's opinions for policy improvement, contributed to the evidence base of health benefits for policy promotion and community collaboration, and revealed interesting gender and regional differences in the opinions. The social media analytics offers significant methodological implications for discovering the public opinions on food policies.