Characterizing diabetes, diet, exercise, and obesity comments on Twitter

作者：

Highlights：

• A multi-component semantic and linguistic framework was proposed to collect Twitter data, discover topics of interest about DDEO, and analyze the topics.

• The characteristics of general public's opinions in regard to diabetes, diet, exercise, and obesity as expressed on 4.5 million tweets were analyzed.

• The public perception of the relationship among diabetes, diet, exercise, and obesity was disclosed.

• The possible practical applications of this research were discussed.

摘要

•A multi-component semantic and linguistic framework was proposed to collect Twitter data, discover topics of interest about DDEO, and analyze the topics.•The characteristics of general public's opinions in regard to diabetes, diet, exercise, and obesity as expressed on 4.5 million tweets were analyzed.•The public perception of the relationship among diabetes, diet, exercise, and obesity was disclosed.•The possible practical applications of this research were discussed.

论文关键词：Health,Diabetes,Diet,Obesity,Exercise,Topic model,Text mining,Twitter

论文评审过程：Received 28 July 2017, Accepted 8 August 2017, Available online 21 September 2017, Version of Record 21 September 2017.

论文官网地址：https://doi.org/10.1016/j.ijinfomgt.2017.08.002