Social media-based overweight prediction using deep learning

Luwen Huangfu, Dajun Zeng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Overweight is epidemic in the United States and elsewhere in the world, causing major health concerns. Based on self-disclosure theory, i.e., people have the tendency to disclose information concerning their feelings, intentions, and acts (e.g., food consumption) online, we aim to leverage social media platforms to develop an unobtrusive approach to predicting overweight. However, traditional statistical and machine learning-based approaches either deliver unsatisfactory performance or demand a large number of features. In this paper, we present a novel social media-based overweight prediction approach based on deep learning as applied in the context of Natural Language Processing (NLP). The input to this approach is food-related Twitter posts. Our computational results show the effectiveness of our method, with remarkable improvement in terms of accuracy over a set of benchmark methods.

Original languageEnglish (US)
Title of host publicationAmericas Conference on Information Systems 2018
Subtitle of host publicationDigital Disruption, AMCIS 2018
PublisherAssociation for Information Systems
ISBN (Print)9780996683166
StatePublished - Jan 1 2018
Event24th Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018 - New Orleans, United States
Duration: Aug 16 2018Aug 18 2018

Publication series

NameAmericas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018

Conference

Conference24th Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018
CountryUnited States
CityNew Orleans
Period8/16/188/18/18

Fingerprint

Learning systems
Health
Processing
Deep learning

Keywords

  • Deep learning
  • Food
  • Language
  • Overweight
  • Public health
  • Twitter

ASJC Scopus subject areas

  • Information Systems

Cite this

Huangfu, L., & Zeng, D. (2018). Social media-based overweight prediction using deep learning. In Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018 (Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018). Association for Information Systems.

Social media-based overweight prediction using deep learning. / Huangfu, Luwen; Zeng, Dajun.

Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018. Association for Information Systems, 2018. (Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Huangfu, L & Zeng, D 2018, Social media-based overweight prediction using deep learning. in Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018. Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018, Association for Information Systems, 24th Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018, New Orleans, United States, 8/16/18.
Huangfu L, Zeng D. Social media-based overweight prediction using deep learning. In Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018. Association for Information Systems. 2018. (Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018).
Huangfu, Luwen ; Zeng, Dajun. / Social media-based overweight prediction using deep learning. Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018. Association for Information Systems, 2018. (Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018).
@inproceedings{714ec0ff910f4561be5c703599f53732,
title = "Social media-based overweight prediction using deep learning",
abstract = "Overweight is epidemic in the United States and elsewhere in the world, causing major health concerns. Based on self-disclosure theory, i.e., people have the tendency to disclose information concerning their feelings, intentions, and acts (e.g., food consumption) online, we aim to leverage social media platforms to develop an unobtrusive approach to predicting overweight. However, traditional statistical and machine learning-based approaches either deliver unsatisfactory performance or demand a large number of features. In this paper, we present a novel social media-based overweight prediction approach based on deep learning as applied in the context of Natural Language Processing (NLP). The input to this approach is food-related Twitter posts. Our computational results show the effectiveness of our method, with remarkable improvement in terms of accuracy over a set of benchmark methods.",
keywords = "Deep learning, Food, Language, Overweight, Public health, Twitter",
author = "Luwen Huangfu and Dajun Zeng",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
isbn = "9780996683166",
series = "Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018",
publisher = "Association for Information Systems",
booktitle = "Americas Conference on Information Systems 2018",

}

TY - GEN

T1 - Social media-based overweight prediction using deep learning

AU - Huangfu, Luwen

AU - Zeng, Dajun

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Overweight is epidemic in the United States and elsewhere in the world, causing major health concerns. Based on self-disclosure theory, i.e., people have the tendency to disclose information concerning their feelings, intentions, and acts (e.g., food consumption) online, we aim to leverage social media platforms to develop an unobtrusive approach to predicting overweight. However, traditional statistical and machine learning-based approaches either deliver unsatisfactory performance or demand a large number of features. In this paper, we present a novel social media-based overweight prediction approach based on deep learning as applied in the context of Natural Language Processing (NLP). The input to this approach is food-related Twitter posts. Our computational results show the effectiveness of our method, with remarkable improvement in terms of accuracy over a set of benchmark methods.

AB - Overweight is epidemic in the United States and elsewhere in the world, causing major health concerns. Based on self-disclosure theory, i.e., people have the tendency to disclose information concerning their feelings, intentions, and acts (e.g., food consumption) online, we aim to leverage social media platforms to develop an unobtrusive approach to predicting overweight. However, traditional statistical and machine learning-based approaches either deliver unsatisfactory performance or demand a large number of features. In this paper, we present a novel social media-based overweight prediction approach based on deep learning as applied in the context of Natural Language Processing (NLP). The input to this approach is food-related Twitter posts. Our computational results show the effectiveness of our method, with remarkable improvement in terms of accuracy over a set of benchmark methods.

KW - Deep learning

KW - Food

KW - Language

KW - Overweight

KW - Public health

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85054242543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054242543&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85054242543

SN - 9780996683166

T3 - Americas Conference on Information Systems 2018: Digital Disruption, AMCIS 2018

BT - Americas Conference on Information Systems 2018

PB - Association for Information Systems

ER -