An analytical system for user emotion extraction, mental state modeling, and rating

Zongru Shao, Rajarathnam Chandramouli, Koduvayur Subbalakshmi, Constantine T. Boyadjiev

Research output: Contribution to journalArticle

Abstract

Emotion is a crucial indicator of the mental state influenced by environmental cognition, health, and intention. Therefore, modeling emotional patterns from daily communications is useful and vital for behavioral studies. This paper presents an analytical system that combines psycho-linguistics, statistical modeling, and computational algorithms to extract, analyze, and rank users’ emotions from their emails. A new category of twelve emotions is proposed to identify a balanced set of six positive emotions and their negative counterparts, respectively. A lexicon-based algorithm is proposed to extract emotions from individual emails at the sentence level by combining thesaurus and parts-of-speech. A Markov chain model is then proposed for the time-dependent emotion stochastic process. Statistical characterization of the Markov chain model provides insights from four aspects: repetition, revisits, steady states, and emotional stability. Finally, an algorithm is discussed to compute the relative ratings of user emotions and subsequently ranking them from the most emotional to the least. As the verification that the proposed system is able to distinguish detailed emotional behaviors caused by mental activities, the Enron email dataset is used to model emotional patterns from 22 executives who were deemed guilty in the court of law vs. 21 non-guilty. Our analysis demonstrates that the proposed system uncovers emotional patterns that are more distinct compared to the traditional emotion categorizations. It is also observed that the guilty subjects express more positive emotions in their emails compared to their non-guilty counterparts, while they are not more joyous than the non-guilty. Such insights have implications for employee risk assessment in organizations. The proposed approach can also be applied to other related areas such as mental health.

LanguageEnglish (US)
Pages82-96
Number of pages15
JournalExpert Systems With Applications
Volume124
DOIs
StatePublished - Jun 15 2019

Fingerprint

Electronic mail
Markov processes
Health
Computational linguistics
Thesauri
Random processes
Risk assessment
Personnel
Communication

Cite this

@article{8550c2375507424ca7ac5ee71a8151eb,
title = "An analytical system for user emotion extraction, mental state modeling, and rating",
abstract = "Emotion is a crucial indicator of the mental state influenced by environmental cognition, health, and intention. Therefore, modeling emotional patterns from daily communications is useful and vital for behavioral studies. This paper presents an analytical system that combines psycho-linguistics, statistical modeling, and computational algorithms to extract, analyze, and rank users’ emotions from their emails. A new category of twelve emotions is proposed to identify a balanced set of six positive emotions and their negative counterparts, respectively. A lexicon-based algorithm is proposed to extract emotions from individual emails at the sentence level by combining thesaurus and parts-of-speech. A Markov chain model is then proposed for the time-dependent emotion stochastic process. Statistical characterization of the Markov chain model provides insights from four aspects: repetition, revisits, steady states, and emotional stability. Finally, an algorithm is discussed to compute the relative ratings of user emotions and subsequently ranking them from the most emotional to the least. As the verification that the proposed system is able to distinguish detailed emotional behaviors caused by mental activities, the Enron email dataset is used to model emotional patterns from 22 executives who were deemed guilty in the court of law vs. 21 non-guilty. Our analysis demonstrates that the proposed system uncovers emotional patterns that are more distinct compared to the traditional emotion categorizations. It is also observed that the guilty subjects express more positive emotions in their emails compared to their non-guilty counterparts, while they are not more joyous than the non-guilty. Such insights have implications for employee risk assessment in organizations. The proposed approach can also be applied to other related areas such as mental health.",
author = "Zongru Shao and Rajarathnam Chandramouli and Koduvayur Subbalakshmi and Boyadjiev, {Constantine T.}",
year = "2019",
month = "6",
day = "15",
doi = "https://doi.org/10.1016/j.eswa.2019.01.004",
language = "English (US)",
volume = "124",
pages = "82--96",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",

}

An analytical system for user emotion extraction, mental state modeling, and rating. / Shao, Zongru; Chandramouli, Rajarathnam; Subbalakshmi, Koduvayur; Boyadjiev, Constantine T.

In: Expert Systems With Applications, Vol. 124, 15.06.2019, p. 82-96.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An analytical system for user emotion extraction, mental state modeling, and rating

AU - Shao, Zongru

AU - Chandramouli, Rajarathnam

AU - Subbalakshmi, Koduvayur

AU - Boyadjiev, Constantine T.

PY - 2019/6/15

Y1 - 2019/6/15

N2 - Emotion is a crucial indicator of the mental state influenced by environmental cognition, health, and intention. Therefore, modeling emotional patterns from daily communications is useful and vital for behavioral studies. This paper presents an analytical system that combines psycho-linguistics, statistical modeling, and computational algorithms to extract, analyze, and rank users’ emotions from their emails. A new category of twelve emotions is proposed to identify a balanced set of six positive emotions and their negative counterparts, respectively. A lexicon-based algorithm is proposed to extract emotions from individual emails at the sentence level by combining thesaurus and parts-of-speech. A Markov chain model is then proposed for the time-dependent emotion stochastic process. Statistical characterization of the Markov chain model provides insights from four aspects: repetition, revisits, steady states, and emotional stability. Finally, an algorithm is discussed to compute the relative ratings of user emotions and subsequently ranking them from the most emotional to the least. As the verification that the proposed system is able to distinguish detailed emotional behaviors caused by mental activities, the Enron email dataset is used to model emotional patterns from 22 executives who were deemed guilty in the court of law vs. 21 non-guilty. Our analysis demonstrates that the proposed system uncovers emotional patterns that are more distinct compared to the traditional emotion categorizations. It is also observed that the guilty subjects express more positive emotions in their emails compared to their non-guilty counterparts, while they are not more joyous than the non-guilty. Such insights have implications for employee risk assessment in organizations. The proposed approach can also be applied to other related areas such as mental health.

AB - Emotion is a crucial indicator of the mental state influenced by environmental cognition, health, and intention. Therefore, modeling emotional patterns from daily communications is useful and vital for behavioral studies. This paper presents an analytical system that combines psycho-linguistics, statistical modeling, and computational algorithms to extract, analyze, and rank users’ emotions from their emails. A new category of twelve emotions is proposed to identify a balanced set of six positive emotions and their negative counterparts, respectively. A lexicon-based algorithm is proposed to extract emotions from individual emails at the sentence level by combining thesaurus and parts-of-speech. A Markov chain model is then proposed for the time-dependent emotion stochastic process. Statistical characterization of the Markov chain model provides insights from four aspects: repetition, revisits, steady states, and emotional stability. Finally, an algorithm is discussed to compute the relative ratings of user emotions and subsequently ranking them from the most emotional to the least. As the verification that the proposed system is able to distinguish detailed emotional behaviors caused by mental activities, the Enron email dataset is used to model emotional patterns from 22 executives who were deemed guilty in the court of law vs. 21 non-guilty. Our analysis demonstrates that the proposed system uncovers emotional patterns that are more distinct compared to the traditional emotion categorizations. It is also observed that the guilty subjects express more positive emotions in their emails compared to their non-guilty counterparts, while they are not more joyous than the non-guilty. Such insights have implications for employee risk assessment in organizations. The proposed approach can also be applied to other related areas such as mental health.

UR - http://www.scopus.com/inward/record.url?scp=85060330623&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060330623&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.eswa.2019.01.004

DO - https://doi.org/10.1016/j.eswa.2019.01.004

M3 - Article

VL - 124

SP - 82

EP - 96

JO - Expert Systems with Applications

T2 - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -