Color-based visual sentiment for social communication

Mayank Amencherla, Lav R Varshney

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

Abstract

Social media platforms provide rich signal sets to understand the nature of social life, and sentiment analysis techniques have been developed to understand the emotional content of text from sites like Twitter and Facebook. Beyond text however, most social media platforms have images at their core, and communication of images may require quantization. Here, we develop methods and present results on understanding the association between the visual content features of images on the popular social media platform Instagram and the psycholinguistic sentiment of their hashtag descriptors. In particular, we collect several thousand images and analyze several aspects of color to predict image sentiment. These results affirm and clarify several psychological theories on the relationship between color and mood/emotion, such as colorfulness being associated with happiness. The data-driven psychovisual insights into sentiment developed herein can be used to define novel fidelity criteria for designing color quantization schemes.

Original languageEnglish (US)
Title of host publication2017 15th Canadian Workshop on Information Theory, CWIT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509060269
DOIs
StatePublished - Jul 27 2017
Event15th Canadian Workshop on Information Theory, CWIT 2017 - Quebec City, Canada
Duration: Jun 11 2017Jun 14 2017

Publication series

Name2017 15th Canadian Workshop on Information Theory, CWIT 2017

Other

Other15th Canadian Workshop on Information Theory, CWIT 2017
CountryCanada
CityQuebec City
Period6/11/176/14/17

Fingerprint

Color
Communication

Keywords

  • big data
  • color
  • images
  • sentiment analysis
  • social signals

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Information Systems

Cite this

Amencherla, M., & Varshney, L. R. (2017). Color-based visual sentiment for social communication. In 2017 15th Canadian Workshop on Information Theory, CWIT 2017 [7994829] (2017 15th Canadian Workshop on Information Theory, CWIT 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CWIT.2017.7994829

Color-based visual sentiment for social communication. / Amencherla, Mayank; Varshney, Lav R.

2017 15th Canadian Workshop on Information Theory, CWIT 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 7994829 (2017 15th Canadian Workshop on Information Theory, CWIT 2017).

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

Amencherla, M & Varshney, LR 2017, Color-based visual sentiment for social communication. in 2017 15th Canadian Workshop on Information Theory, CWIT 2017., 7994829, 2017 15th Canadian Workshop on Information Theory, CWIT 2017, Institute of Electrical and Electronics Engineers Inc., 15th Canadian Workshop on Information Theory, CWIT 2017, Quebec City, Canada, 6/11/17. https://doi.org/10.1109/CWIT.2017.7994829
Amencherla M, Varshney LR. Color-based visual sentiment for social communication. In 2017 15th Canadian Workshop on Information Theory, CWIT 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 7994829. (2017 15th Canadian Workshop on Information Theory, CWIT 2017). https://doi.org/10.1109/CWIT.2017.7994829
Amencherla, Mayank ; Varshney, Lav R. / Color-based visual sentiment for social communication. 2017 15th Canadian Workshop on Information Theory, CWIT 2017. Institute of Electrical and Electronics Engineers Inc., 2017. (2017 15th Canadian Workshop on Information Theory, CWIT 2017).
@inproceedings{9dc4e1b395544667aba12caee90fde32,
title = "Color-based visual sentiment for social communication",
abstract = "Social media platforms provide rich signal sets to understand the nature of social life, and sentiment analysis techniques have been developed to understand the emotional content of text from sites like Twitter and Facebook. Beyond text however, most social media platforms have images at their core, and communication of images may require quantization. Here, we develop methods and present results on understanding the association between the visual content features of images on the popular social media platform Instagram and the psycholinguistic sentiment of their hashtag descriptors. In particular, we collect several thousand images and analyze several aspects of color to predict image sentiment. These results affirm and clarify several psychological theories on the relationship between color and mood/emotion, such as colorfulness being associated with happiness. The data-driven psychovisual insights into sentiment developed herein can be used to define novel fidelity criteria for designing color quantization schemes.",
keywords = "big data, color, images, sentiment analysis, social signals",
author = "Mayank Amencherla and Varshney, {Lav R}",
year = "2017",
month = "7",
day = "27",
doi = "10.1109/CWIT.2017.7994829",
language = "English (US)",
series = "2017 15th Canadian Workshop on Information Theory, CWIT 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2017 15th Canadian Workshop on Information Theory, CWIT 2017",
address = "United States",

}

TY - GEN

T1 - Color-based visual sentiment for social communication

AU - Amencherla, Mayank

AU - Varshney, Lav R

PY - 2017/7/27

Y1 - 2017/7/27

N2 - Social media platforms provide rich signal sets to understand the nature of social life, and sentiment analysis techniques have been developed to understand the emotional content of text from sites like Twitter and Facebook. Beyond text however, most social media platforms have images at their core, and communication of images may require quantization. Here, we develop methods and present results on understanding the association between the visual content features of images on the popular social media platform Instagram and the psycholinguistic sentiment of their hashtag descriptors. In particular, we collect several thousand images and analyze several aspects of color to predict image sentiment. These results affirm and clarify several psychological theories on the relationship between color and mood/emotion, such as colorfulness being associated with happiness. The data-driven psychovisual insights into sentiment developed herein can be used to define novel fidelity criteria for designing color quantization schemes.

AB - Social media platforms provide rich signal sets to understand the nature of social life, and sentiment analysis techniques have been developed to understand the emotional content of text from sites like Twitter and Facebook. Beyond text however, most social media platforms have images at their core, and communication of images may require quantization. Here, we develop methods and present results on understanding the association between the visual content features of images on the popular social media platform Instagram and the psycholinguistic sentiment of their hashtag descriptors. In particular, we collect several thousand images and analyze several aspects of color to predict image sentiment. These results affirm and clarify several psychological theories on the relationship between color and mood/emotion, such as colorfulness being associated with happiness. The data-driven psychovisual insights into sentiment developed herein can be used to define novel fidelity criteria for designing color quantization schemes.

KW - big data

KW - color

KW - images

KW - sentiment analysis

KW - social signals

UR - http://www.scopus.com/inward/record.url?scp=85028568757&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028568757&partnerID=8YFLogxK

U2 - 10.1109/CWIT.2017.7994829

DO - 10.1109/CWIT.2017.7994829

M3 - Conference contribution

AN - SCOPUS:85028568757

T3 - 2017 15th Canadian Workshop on Information Theory, CWIT 2017

BT - 2017 15th Canadian Workshop on Information Theory, CWIT 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -