Big Social Data Analytics for Public Health: Predicting Facebook Post Performance Using Artificial Neural Networks and Deep Learning

Nadiya Straton; Raghava Rao Mukkamala; Ravi Vatrapu

doi:10.1109/BigDataCongress.2017.21

Big Social Data Analytics for Public Health: Predicting Facebook Post Performance Using Artificial Neural Networks and Deep Learning

Nadiya Straton, Raghava Rao Mukkamala, Ravi Vatrapu

Department of Digitalization

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

Abstract

Facebook ”post popularity” analysis is fundamental for differentiating between relevant posts and posts with low user engagement and consequently their characteristics. This research study aims at health and care organizations to improve information dissemination on social media platforms by reducing clutter and noise. At the same time, it will help users navigate through vast amount of information in direction of the relevant health and care content. Furthermore, study explores prediction of popularity of healthcare posts on the largest social media platform Facebook. Methodology is presented in this paper to predict user engagement based on eleven characteristics of the post: Post Type, Hour Span, Facebook Wall Category, Level, Country, isHoliday, Season, Created Year, Month, Day of the Week, Time of the Day. Finally, post performance prediction is conducted using Artificial Neural Networks (ANN) and Deep Neural Networks (DNN). Different network topology measures
are used to achieve best accuracy prediction followed by examples and discussion on why DNN might not be optimal technique for the given data set.

Original language	English
Title of host publication	Proceedings of the 6th IEEE International Congress on Big Data. BigData Congress 2017
Editors	George Karypis, Jia Zhang
Number of pages	8
Place of Publication	Los Alamitos, CA
Publisher	IEEE
Publication date	2017
Pages	89-96
ISBN (Print)	9781538619964
ISBN (Electronic)	9781538619957, 9781538619971
DOIs	https://doi.org/10.1109/BigDataCongress.2017.21
Publication status	Published - 2017
Event	6th IEEE International Congress on Big Data. BigData Congress 2017 - Hilton Hawaiian Village Waikiki Beach Resort, Honolulu, United States Duration: 25 Jun 2017 → 30 Jun 2017 Conference number: 6 http://www.bigdatacongress.org/2017/

Conference

Conference	6th IEEE International Congress on Big Data. BigData Congress 2017
Number	6
Location	Hilton Hawaiian Village Waikiki Beach Resort
Country/Territory	United States
City	Honolulu
Period	25/06/2017 → 30/06/2017
Internet address	http://www.bigdatacongress.org/2017/

Keywords

Post performance
Artificial neural network (ANN)
Deep neural network (DNN)
Negative entropy
Purity

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/BigDataCongress.2017.21Licence: Unspecified

Handle.net

Persistent link

Cite this

Straton, N., Mukkamala, R. R., & Vatrapu, R. (2017). Big Social Data Analytics for Public Health: Predicting Facebook Post Performance Using Artificial Neural Networks and Deep Learning. In G. Karypis, & J. Zhang (Eds.), Proceedings of the 6th IEEE International Congress on Big Data. BigData Congress 2017 (pp. 89-96). IEEE. https://doi.org/10.1109/BigDataCongress.2017.21

@inproceedings{afed6ec8a32a476e9a2a60ef4cadbb21,

title = "Big Social Data Analytics for Public Health: Predicting Facebook Post Performance Using Artificial Neural Networks and Deep Learning",

abstract = "Facebook ”post popularity” analysis is fundamental for differentiating between relevant posts and posts with low user engagement and consequently their characteristics. This research study aims at health and care organizations to improve information dissemination on social media platforms by reducing clutter and noise. At the same time, it will help users navigate through vast amount of information in direction of the relevant health and care content. Furthermore, study explores prediction of popularity of healthcare posts on the largest social media platform Facebook. Methodology is presented in this paper to predict user engagement based on eleven characteristics of the post: Post Type, Hour Span, Facebook Wall Category, Level, Country, isHoliday, Season, Created Year, Month, Day of the Week, Time of the Day. Finally, post performance prediction is conducted using Artificial Neural Networks (ANN) and Deep Neural Networks (DNN). Different network topology measuresare used to achieve best accuracy prediction followed by examples and discussion on why DNN might not be optimal technique for the given data set.",

keywords = "Post performance, Artificial neural network (ANN), Deep neural network (DNN), Negative entropy, Purity, Post performance, Artificial neural network (ANN), Deep neural network (DNN), Negative entropy, Purity",

author = "Nadiya Straton and Mukkamala, {Raghava Rao} and Ravi Vatrapu",

year = "2017",

doi = "10.1109/BigDataCongress.2017.21",

language = "English",

isbn = "9781538619964",

pages = "89--96",

editor = "George Karypis and Jia Zhang",

booktitle = "Proceedings of the 6th IEEE International Congress on Big Data. BigData Congress 2017",

publisher = "IEEE",

address = "United States",

note = "6th IEEE International Congress on Big Data. BigData Congress 2017 ; Conference date: 25-06-2017 Through 30-06-2017",

url = "http://www.bigdatacongress.org/2017/",

}

Straton, N , Mukkamala, RR & Vatrapu, R 2017, Big Social Data Analytics for Public Health: Predicting Facebook Post Performance Using Artificial Neural Networks and Deep Learning. in G Karypis & J Zhang (eds), Proceedings of the 6th IEEE International Congress on Big Data. BigData Congress 2017. IEEE, Los Alamitos, CA, pp. 89-96, 6th IEEE International Congress on Big Data. BigData Congress 2017, Honolulu, Hawaii, United States, 25/06/2017. https://doi.org/10.1109/BigDataCongress.2017.21

Big Social Data Analytics for Public Health: Predicting Facebook Post Performance Using Artificial Neural Networks and Deep Learning. / Straton, Nadiya ; Mukkamala, Raghava Rao ; Vatrapu, Ravi.
Proceedings of the 6th IEEE International Congress on Big Data. BigData Congress 2017. ed. / George Karypis; Jia Zhang. Los Alamitos, CA: IEEE, 2017. p. 89-96.

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

TY - GEN

T1 - Big Social Data Analytics for Public Health

T2 - 6th IEEE International Congress on Big Data. BigData Congress 2017

AU - Straton, Nadiya

AU - Mukkamala, Raghava Rao

AU - Vatrapu, Ravi

N1 - Conference code: 6

PY - 2017

Y1 - 2017

N2 - Facebook ”post popularity” analysis is fundamental for differentiating between relevant posts and posts with low user engagement and consequently their characteristics. This research study aims at health and care organizations to improve information dissemination on social media platforms by reducing clutter and noise. At the same time, it will help users navigate through vast amount of information in direction of the relevant health and care content. Furthermore, study explores prediction of popularity of healthcare posts on the largest social media platform Facebook. Methodology is presented in this paper to predict user engagement based on eleven characteristics of the post: Post Type, Hour Span, Facebook Wall Category, Level, Country, isHoliday, Season, Created Year, Month, Day of the Week, Time of the Day. Finally, post performance prediction is conducted using Artificial Neural Networks (ANN) and Deep Neural Networks (DNN). Different network topology measuresare used to achieve best accuracy prediction followed by examples and discussion on why DNN might not be optimal technique for the given data set.

AB - Facebook ”post popularity” analysis is fundamental for differentiating between relevant posts and posts with low user engagement and consequently their characteristics. This research study aims at health and care organizations to improve information dissemination on social media platforms by reducing clutter and noise. At the same time, it will help users navigate through vast amount of information in direction of the relevant health and care content. Furthermore, study explores prediction of popularity of healthcare posts on the largest social media platform Facebook. Methodology is presented in this paper to predict user engagement based on eleven characteristics of the post: Post Type, Hour Span, Facebook Wall Category, Level, Country, isHoliday, Season, Created Year, Month, Day of the Week, Time of the Day. Finally, post performance prediction is conducted using Artificial Neural Networks (ANN) and Deep Neural Networks (DNN). Different network topology measuresare used to achieve best accuracy prediction followed by examples and discussion on why DNN might not be optimal technique for the given data set.

KW - Post performance

KW - Artificial neural network (ANN)

KW - Deep neural network (DNN)

KW - Negative entropy

KW - Purity

KW - Post performance

KW - Artificial neural network (ANN)

KW - Deep neural network (DNN)

KW - Negative entropy

KW - Purity

U2 - 10.1109/BigDataCongress.2017.21

DO - 10.1109/BigDataCongress.2017.21

M3 - Article in proceedings

SN - 9781538619964

SP - 89

EP - 96

BT - Proceedings of the 6th IEEE International Congress on Big Data. BigData Congress 2017

A2 - Karypis, George

A2 - Zhang, Jia

PB - IEEE

CY - Los Alamitos, CA

Y2 - 25 June 2017 through 30 June 2017

ER -