A preliminary investigation with twitter to augment CVD exposome research

Daniel Medina Sada; Susan Mengel; Lisaann S. Gittner; Hafiz Khan; Mario A. Pitalua Rodriguez; Ravi Vadapalli

doi:10.1145/3148055.3148074

A preliminary investigation with twitter to augment CVD exposome research

Daniel Medina Sada, Susan Mengel, Lisaann S. Gittner, Hafiz Khan, Mario A. Pitalua Rodriguez, Ravi Vadapalli

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

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.

Original language	English
Title of host publication	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
Number of pages	10
ISBN (Electronic)	9781450355490
DOIs	https://doi.org/10.1145/3148055.3148074
State	Published - Dec 5 2017
Event	4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2017 - Austin, United States Duration: Dec 5 2017 → Dec 8 2017

Publication series

Name	BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies

Conference

Conference	4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2017
Country/Territory	United States
City	Austin
Period	12/5/17 → 12/8/17

Keywords

Data Mining, Text Analysis
Healthcare
Sentiment Analysis
Topical Analysis
Twitter

Access to Document

10.1145/3148055.3148074

Cite this

Sada, D. M., Mengel, S., Gittner, L. S., Khan, H., Pitalua Rodriguez, M. A., & Vadapalli, R. (2017). A preliminary investigation with twitter to augment CVD exposome research. In BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (pp. 169-178). (BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies). Association for Computing Machinery, Inc. https://doi.org/10.1145/3148055.3148074

Sada, Daniel Medina ; Mengel, Susan ; Gittner, Lisaann S. ; Khan, Hafiz ; Pitalua Rodriguez, Mario A. ; Vadapalli, Ravi. / A preliminary investigation with twitter to augment CVD exposome research. BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies. Association for Computing Machinery, Inc, 2017. pp. 169-178 (BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies).

@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",

}

Sada, DM, Mengel, S, Gittner, LS, Khan, H, Pitalua Rodriguez, MA & Vadapalli, R 2017, A preliminary investigation with twitter to augment CVD exposome research. in BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies. BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, Association for Computing Machinery, Inc, pp. 169-178, 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2017, Austin, United States, 12/5/17. https://doi.org/10.1145/3148055.3148074

A preliminary investigation with twitter to augment CVD exposome research. / Sada, Daniel Medina; Mengel, Susan; Gittner, Lisaann S.; Khan, Hafiz; Pitalua Rodriguez, Mario A.; Vadapalli, Ravi.

BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies. Association for Computing Machinery, Inc, 2017. p. 169-178 (BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A preliminary investigation with twitter to augment CVD exposome research

AU - Sada, Daniel Medina

AU - Mengel, Susan

AU - Gittner, Lisaann S.

AU - Khan, Hafiz

AU - Pitalua Rodriguez, Mario A.

AU - Vadapalli, Ravi

PY - 2017/12/5

Y1 - 2017/12/5

N2 - 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.

AB - 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.

KW - Data Mining, Text Analysis

KW - Healthcare

KW - Sentiment Analysis

KW - Topical Analysis

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85058266220&partnerID=8YFLogxK

U2 - 10.1145/3148055.3148074

DO - 10.1145/3148055.3148074

M3 - Conference contribution

AN - SCOPUS:85058266220

T3 - BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies

SP - 169

EP - 178

BT - BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies

PB - Association for Computing Machinery, Inc

Y2 - 5 December 2017 through 8 December 2017

ER -

Sada DM, Mengel S, Gittner LS, Khan H, Pitalua Rodriguez MA, Vadapalli R. A preliminary investigation with twitter to augment CVD exposome research. In BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies. Association for Computing Machinery, Inc. 2017. p. 169-178. (BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies). https://doi.org/10.1145/3148055.3148074

A preliminary investigation with twitter to augment CVD exposome research

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this