@inproceedings{e0df15e23a124cfb9bee23036485b63a,
title = "A preliminary investigation with twitter to augment CVD exposome research",
abstract = "This project focuses on analyzing the sentiment of tweets in order to find a correspondence to health issues and to gain a new perspective in analyzing health data. Twitter social media is a huge source of information that can augment data about health in particular geographic locations. For this project, analyzing tweets is an attempt to find some relation between the sentiment of tweets and Cardiovascular Disease (CVD) in the counties along Interstate 20 (I-20) in Texas. Only geo-tagged tweets that are mapped to the counties of interest are used in the main analysis. The sentiment of the text of the Tweet is determined as being either positive or negative. Using the Natural Language Toolkit (NLTK), several classifiers are trained to determine the sentiment of the tweet. Each of the classifier's results are compared to measure the confidence of the sentiment declared. After all the tweets are classified, then the results are used to calculate the following for each county: Positive-to-Negative ratio, Positive-to-Population ratio, and Negative-to-Population ratio. This data is then separated into quintiles and compared to the Cardiovascular Disease map of I-20 in order to determine if a relationship may exist between CVD and the tweets. The preliminary results show that a correspondence exists between the low CVD rate in a county to the Positive-to-Negative ratio of that same county.",
keywords = "Data Mining, Text Analysis, Healthcare, Sentiment Analysis, Topical Analysis, Twitter",
author = "Sada, {Daniel Medina} and Susan Mengel and Gittner, {Lisaann S.} and Hafiz Khan and {Pitalua Rodriguez}, {Mario A.} and Ravi Vadapalli",
note = "Publisher Copyright: {\textcopyright} 2017 Association for Computing Machinery.; null ; Conference date: 05-12-2017 Through 08-12-2017",
year = "2017",
month = dec,
day = "5",
doi = "10.1145/3148055.3148074",
language = "English",
series = "BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies",
publisher = "Association for Computing Machinery, Inc",
pages = "169--178",
booktitle = "BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies",
}