A Supervised Machine Learning Study of Online Discussion Forums about Type-2 Diabetes

Jonathan-Raphael Reichert, Klaus Langholz Kristensen, Raghava Rao Mukkamala, Ravi Vatrapu

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

As an instance of online communities, online diabetes discussion forums mirror these characteristics and seem to track the growing impact of diabetes on individuals around the world. In this paper, we first systematically collected texts
from online discussion forums about diabetes and then applied supervised machine learning techniques to analyze the online conversations. In order to analyse these online textual conversations, we have chosen four domain specific models (Emotions, Sentiment, Personality Traits and Patient Journey). As part of text classification, we employed the ensemble learning method by using 5 different supervised machine learning algorithms to build a set of text classifiers by using the voting method to predict most probable label for a given textual conversation from the online discussion forums. Our findings show that there is a high amount of trust expressed by a subset of users and these users play a vital role in supporting other users of the online discussion forums about diabetes.
As an instance of online communities, online diabetes discussion forums mirror these characteristics and seem to track the growing impact of diabetes on individuals around the world. In this paper, we first systematically collected texts
from online discussion forums about diabetes and then applied supervised machine learning techniques to analyze the online conversations. In order to analyse these online textual conversations, we have chosen four domain specific models (Emotions, Sentiment, Personality Traits and Patient Journey). As part of text classification, we employed the ensemble learning method by using 5 different supervised machine learning algorithms to build a set of text classifiers by using the voting method to predict most probable label for a given textual conversation from the online discussion forums. Our findings show that there is a high amount of trust expressed by a subset of users and these users play a vital role in supporting other users of the online discussion forums about diabetes.
LanguageEnglish
Title of host publication2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom)
EditorsHsi Pin Ma, Baofeng Wang
Place of PublicationLos Alamos, CA
PublisherIEEE
Date2017
Pages1-7
ISBN (Print)9781509067039, 9781509067053
ISBN (Electronic)9781509067046
DOIs
StatePublished - 2017
EventIEEE Healthcom 17: 19th International Conference on e-Health Networking, Applications & Services - Dalian, China
Duration: 12 Oct 201715 Oct 2017
Conference number: 19
http://healthcom2017.ieee-healthcom.org

Conference

ConferenceIEEE Healthcom 17
Number19
CountryChina
CityDalian
Period12/10/201715/10/2017
SponsorDalian University
Internet address

Bibliographical note

CBS Library does not have access to the material

Cite this

Reichert, J-R., Kristensen, K. L., Mukkamala, R. R., & Vatrapu, R. (2017). A Supervised Machine Learning Study of Online Discussion Forums about Type-2 Diabetes. In H. P. Ma, & B. Wang (Eds.), 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom) (pp. 1-7). Los Alamos, CA: IEEE. DOI: 10.1109/HealthCom.2017.8210815
Reichert, Jonathan-Raphael ; Kristensen, Klaus Langholz ; Mukkamala, Raghava Rao ; Vatrapu, Ravi. / A Supervised Machine Learning Study of Online Discussion Forums about Type-2 Diabetes. 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom). editor / Hsi Pin Ma ; Baofeng Wang. Los Alamos, CA : IEEE, 2017. pp. 1-7
@inproceedings{88244588b331476283ee6651c5e76a74,
title = "A Supervised Machine Learning Study of Online Discussion Forums about Type-2 Diabetes",
abstract = "As an instance of online communities, online diabetes discussion forums mirror these characteristics and seem to track the growing impact of diabetes on individuals around the world. In this paper, we first systematically collected textsfrom online discussion forums about diabetes and then applied supervised machine learning techniques to analyze the online conversations. In order to analyse these online textual conversations, we have chosen four domain specific models (Emotions, Sentiment, Personality Traits and Patient Journey). As part of text classification, we employed the ensemble learning method by using 5 different supervised machine learning algorithms to build a set of text classifiers by using the voting method to predict most probable label for a given textual conversation from the online discussion forums. Our findings show that there is a high amount of trust expressed by a subset of users and these users play a vital role in supporting other users of the online discussion forums about diabetes.",
author = "Jonathan-Raphael Reichert and Kristensen, {Klaus Langholz} and Mukkamala, {Raghava Rao} and Ravi Vatrapu",
note = "CBS Library does not have access to the material",
year = "2017",
doi = "10.1109/HealthCom.2017.8210815",
language = "English",
isbn = "9781509067039",
pages = "1--7",
editor = "Ma, {Hsi Pin} and Baofeng Wang",
booktitle = "2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom)",
publisher = "IEEE",
address = "United States",

}

Reichert, J-R, Kristensen, KL, Mukkamala, RR & Vatrapu, R 2017, A Supervised Machine Learning Study of Online Discussion Forums about Type-2 Diabetes. in HP Ma & B Wang (eds), 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom). IEEE, Los Alamos, CA, pp. 1-7, IEEE Healthcom 17, Dalian, China, 12/10/2017. DOI: 10.1109/HealthCom.2017.8210815

A Supervised Machine Learning Study of Online Discussion Forums about Type-2 Diabetes. / Reichert, Jonathan-Raphael; Kristensen, Klaus Langholz; Mukkamala, Raghava Rao; Vatrapu, Ravi.

2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom). ed. / Hsi Pin Ma; Baofeng Wang. Los Alamos, CA : IEEE, 2017. p. 1-7.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - A Supervised Machine Learning Study of Online Discussion Forums about Type-2 Diabetes

AU - Reichert,Jonathan-Raphael

AU - Kristensen,Klaus Langholz

AU - Mukkamala,Raghava Rao

AU - Vatrapu,Ravi

N1 - CBS Library does not have access to the material

PY - 2017

Y1 - 2017

N2 - As an instance of online communities, online diabetes discussion forums mirror these characteristics and seem to track the growing impact of diabetes on individuals around the world. In this paper, we first systematically collected textsfrom online discussion forums about diabetes and then applied supervised machine learning techniques to analyze the online conversations. In order to analyse these online textual conversations, we have chosen four domain specific models (Emotions, Sentiment, Personality Traits and Patient Journey). As part of text classification, we employed the ensemble learning method by using 5 different supervised machine learning algorithms to build a set of text classifiers by using the voting method to predict most probable label for a given textual conversation from the online discussion forums. Our findings show that there is a high amount of trust expressed by a subset of users and these users play a vital role in supporting other users of the online discussion forums about diabetes.

AB - As an instance of online communities, online diabetes discussion forums mirror these characteristics and seem to track the growing impact of diabetes on individuals around the world. In this paper, we first systematically collected textsfrom online discussion forums about diabetes and then applied supervised machine learning techniques to analyze the online conversations. In order to analyse these online textual conversations, we have chosen four domain specific models (Emotions, Sentiment, Personality Traits and Patient Journey). As part of text classification, we employed the ensemble learning method by using 5 different supervised machine learning algorithms to build a set of text classifiers by using the voting method to predict most probable label for a given textual conversation from the online discussion forums. Our findings show that there is a high amount of trust expressed by a subset of users and these users play a vital role in supporting other users of the online discussion forums about diabetes.

U2 - 10.1109/HealthCom.2017.8210815

DO - 10.1109/HealthCom.2017.8210815

M3 - Article in proceedings

SN - 9781509067039

SN - 9781509067053

SP - 1

EP - 7

BT - 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom)

PB - IEEE

CY - Los Alamos, CA

ER -

Reichert J-R, Kristensen KL, Mukkamala RR, Vatrapu R. A Supervised Machine Learning Study of Online Discussion Forums about Type-2 Diabetes. In Ma HP, Wang B, editors, 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom). Los Alamos, CA: IEEE. 2017. p. 1-7. Available from, DOI: 10.1109/HealthCom.2017.8210815