A fuzzy computational model of emotion for cloud based sentiment analysis

Charalampos Karyotis, Faiyaz Doctor, Rahat Iqbal, Anne James, V. Chang

Abstract

This paper presents a novel emotion modeling methodology for incorporating human emotion into intelligent computer systems. The proposed approach includes a method to elicit emotion information from users, a new representation of emotion (AV-AT model) that is modelled using a genetically optimized adaptive Fuzzy Logic technique, and a framework for predicting and tracking user’s affective trajectory over time. The fuzzy technique is evaluated in terms of its ability to model affective states in comparison to other existing machine learning approaches. The performance of the proposed affect modeling methodology is tested through the deployment of a personalised learning system, and series of offline and online experiments. A hybrid cloud intelligence infrastructure is used to conduct large-scale experiments to analyze user sentiments and associated emotions, using data from a million Facebook users. A performance analysis of the infrastructure on processing, analyzing, and data storage has been carried out, illustrating its viability for large-scale data processing tasks. A comparison of the proposed emotion categorizing approach with Facebook’s sentiment analysis API demonstrates that our approach can achieve comparable performance. Finally, discussions on research contributions to cloud intelligence using sentiment analysis, emotion modeling, big data, and comparisons with other approaches are presented in detail.
Original languageEnglish
JournalInformation Sciences
Volume(in press)
DOIs
StatePublished - 10 Feb 2017

Fingerprint

Learning systems
Experiments
Application programming interfaces (API)
Fuzzy logic
Computer systems
Trajectories
Big data

Keywords

  • Hybrid cloud
  • Big data
  • Emotion modeling
  • Affective computing
  • Adaptive fuzzy systems
  • Social network sentiment analysis

Cite this

A fuzzy computational model of emotion for cloud based sentiment analysis. / Karyotis, Charalampos; Doctor, Faiyaz; Iqbal, Rahat; James, Anne; Chang, V.

In: Information Sciences, Vol. (in press), 10.02.2017.

Research output: Contribution to journalArticle

Karyotis, Charalampos; Doctor, Faiyaz; Iqbal, Rahat; James, Anne; Chang, V. / A fuzzy computational model of emotion for cloud based sentiment analysis.

In: Information Sciences, Vol. (in press), 10.02.2017.

Research output: Contribution to journalArticle

@article{2f553e989c3f44d49ee44e0ab0a02640,
title = "A fuzzy computational model of emotion for cloud based sentiment analysis",
abstract = "This paper presents a novel emotion modeling methodology for incorporating human emotion into intelligent computer systems. The proposed approach includes a method to elicit emotion information from users, a new representation of emotion (AV-AT model) that is modelled using a genetically optimized adaptive Fuzzy Logic technique, and a framework for predicting and tracking user’s affective trajectory over time. The fuzzy technique is evaluated in terms of its ability to model affective states in comparison to other existing machine learning approaches. The performance of the proposed affect modeling methodology is tested through the deployment of a personalised learning system, and series of offline and online experiments. A hybrid cloud intelligence infrastructure is used to conduct large-scale experiments to analyze user sentiments and associated emotions, using data from a million Facebook users. A performance analysis of the infrastructure on processing, analyzing, and data storage has been carried out, illustrating its viability for large-scale data processing tasks. A comparison of the proposed emotion categorizing approach with Facebook’s sentiment analysis API demonstrates that our approach can achieve comparable performance. Finally, discussions on research contributions to cloud intelligence using sentiment analysis, emotion modeling, big data, and comparisons with other approaches are presented in detail.",
keywords = "Hybrid cloud, Big data, Emotion modeling, Affective computing, Adaptive fuzzy systems, Social network sentiment analysis",
author = "Charalampos Karyotis and Faiyaz Doctor and Rahat Iqbal and Anne James and V. Chang",
note = "Due to publisher policy, the full text is not available on the repository until the 10th of February 2018. This article is currently in press. Full citation details will be uploaded when available.",
year = "2017",
month = "2",
doi = "10.1016/j.ins.2017.02.004",
volume = "(in press)",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier",

}

TY - JOUR

T1 - A fuzzy computational model of emotion for cloud based sentiment analysis

AU - Karyotis,Charalampos

AU - Doctor,Faiyaz

AU - Iqbal,Rahat

AU - James,Anne

AU - Chang,V.

N1 - Due to publisher policy, the full text is not available on the repository until the 10th of February 2018. This article is currently in press. Full citation details will be uploaded when available.

PY - 2017/2/10

Y1 - 2017/2/10

N2 - This paper presents a novel emotion modeling methodology for incorporating human emotion into intelligent computer systems. The proposed approach includes a method to elicit emotion information from users, a new representation of emotion (AV-AT model) that is modelled using a genetically optimized adaptive Fuzzy Logic technique, and a framework for predicting and tracking user’s affective trajectory over time. The fuzzy technique is evaluated in terms of its ability to model affective states in comparison to other existing machine learning approaches. The performance of the proposed affect modeling methodology is tested through the deployment of a personalised learning system, and series of offline and online experiments. A hybrid cloud intelligence infrastructure is used to conduct large-scale experiments to analyze user sentiments and associated emotions, using data from a million Facebook users. A performance analysis of the infrastructure on processing, analyzing, and data storage has been carried out, illustrating its viability for large-scale data processing tasks. A comparison of the proposed emotion categorizing approach with Facebook’s sentiment analysis API demonstrates that our approach can achieve comparable performance. Finally, discussions on research contributions to cloud intelligence using sentiment analysis, emotion modeling, big data, and comparisons with other approaches are presented in detail.

AB - This paper presents a novel emotion modeling methodology for incorporating human emotion into intelligent computer systems. The proposed approach includes a method to elicit emotion information from users, a new representation of emotion (AV-AT model) that is modelled using a genetically optimized adaptive Fuzzy Logic technique, and a framework for predicting and tracking user’s affective trajectory over time. The fuzzy technique is evaluated in terms of its ability to model affective states in comparison to other existing machine learning approaches. The performance of the proposed affect modeling methodology is tested through the deployment of a personalised learning system, and series of offline and online experiments. A hybrid cloud intelligence infrastructure is used to conduct large-scale experiments to analyze user sentiments and associated emotions, using data from a million Facebook users. A performance analysis of the infrastructure on processing, analyzing, and data storage has been carried out, illustrating its viability for large-scale data processing tasks. A comparison of the proposed emotion categorizing approach with Facebook’s sentiment analysis API demonstrates that our approach can achieve comparable performance. Finally, discussions on research contributions to cloud intelligence using sentiment analysis, emotion modeling, big data, and comparisons with other approaches are presented in detail.

KW - Hybrid cloud

KW - Big data

KW - Emotion modeling

KW - Affective computing

KW - Adaptive fuzzy systems

KW - Social network sentiment analysis

U2 - 10.1016/j.ins.2017.02.004

DO - 10.1016/j.ins.2017.02.004

M3 - Article

VL - (in press)

JO - Information Sciences

T2 - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -