Comparing ESM timings for emotional estimation model with fine temporal granularity

Wataru Sasaki, Jin Nakazawa, Tadashi Okoshi

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

1 Citation (Scopus)

Abstract

Towards wellbeing-awareness in computing, researches for estimating users' emotions using smartphone sensor data have been actively conducted as smartphones are getting more and more ubiquitous. Most studies have constructed emotion estimation models based on machine learning with contextual data from the smartphones and user's self-reporting ground truth label often collected via Experience Sampling Method (ESM). However, snice our emotion changes frequently in our daily lives, trying to collect the ground truth of such volatile emotions leads a storm of ESMs which could be burden to the users. In order to find better ESM methods, we propose and compare 3 ESMs, namely Randomized ESM that executes in randomly timings, Trigger ESM that executes when the user's behavior changes, and Unlocking ESM that sets up ESM on the unlocking screen. We constructed various emotional estimation models with four types of time granularity (1 day, 1/3 day, 3 hours, 1 hour) in four weeks experience with eight persons. As for the response rate, Unlocking ESM was the highest. In addition, it was clear that Unlocking ESM had the highest estimation accuracy in most cases.

Original languageEnglish
Title of host publicationUbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers
PublisherAssociation for Computing Machinery, Inc
Pages722-725
Number of pages4
ISBN (Electronic)9781450359665
DOIs
Publication statusPublished - 2018 Oct 8
Event2018 Joint ACM International Conference on Pervasive and Ubiquitous Computing, UbiComp 2018 and 2018 ACM International Symposium on Wearable Computers, ISWC 2018 - Singapore, Singapore
Duration: 2018 Oct 82018 Oct 12

Other

Other2018 Joint ACM International Conference on Pervasive and Ubiquitous Computing, UbiComp 2018 and 2018 ACM International Symposium on Wearable Computers, ISWC 2018
CountrySingapore
CitySingapore
Period18/10/818/10/12

Fingerprint

Sampling
Smartphones
Learning systems
Labels
Sensors

Keywords

  • Affective computing
  • Emotions
  • ESM
  • Human factors
  • Smartphone usage

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Information Systems

Cite this

Sasaki, W., Nakazawa, J., & Okoshi, T. (2018). Comparing ESM timings for emotional estimation model with fine temporal granularity. In UbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers (pp. 722-725). Association for Computing Machinery, Inc. https://doi.org/10.1145/3267305.3267699

Comparing ESM timings for emotional estimation model with fine temporal granularity. / Sasaki, Wataru; Nakazawa, Jin; Okoshi, Tadashi.

UbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc, 2018. p. 722-725.

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

Sasaki, W, Nakazawa, J & Okoshi, T 2018, Comparing ESM timings for emotional estimation model with fine temporal granularity. in UbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc, pp. 722-725, 2018 Joint ACM International Conference on Pervasive and Ubiquitous Computing, UbiComp 2018 and 2018 ACM International Symposium on Wearable Computers, ISWC 2018, Singapore, Singapore, 18/10/8. https://doi.org/10.1145/3267305.3267699
Sasaki W, Nakazawa J, Okoshi T. Comparing ESM timings for emotional estimation model with fine temporal granularity. In UbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc. 2018. p. 722-725 https://doi.org/10.1145/3267305.3267699
Sasaki, Wataru ; Nakazawa, Jin ; Okoshi, Tadashi. / Comparing ESM timings for emotional estimation model with fine temporal granularity. UbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc, 2018. pp. 722-725
@inproceedings{755bdea7e04249d7b4b0922535347647,
title = "Comparing ESM timings for emotional estimation model with fine temporal granularity",
abstract = "Towards wellbeing-awareness in computing, researches for estimating users' emotions using smartphone sensor data have been actively conducted as smartphones are getting more and more ubiquitous. Most studies have constructed emotion estimation models based on machine learning with contextual data from the smartphones and user's self-reporting ground truth label often collected via Experience Sampling Method (ESM). However, snice our emotion changes frequently in our daily lives, trying to collect the ground truth of such volatile emotions leads a storm of ESMs which could be burden to the users. In order to find better ESM methods, we propose and compare 3 ESMs, namely Randomized ESM that executes in randomly timings, Trigger ESM that executes when the user's behavior changes, and Unlocking ESM that sets up ESM on the unlocking screen. We constructed various emotional estimation models with four types of time granularity (1 day, 1/3 day, 3 hours, 1 hour) in four weeks experience with eight persons. As for the response rate, Unlocking ESM was the highest. In addition, it was clear that Unlocking ESM had the highest estimation accuracy in most cases.",
keywords = "Affective computing, Emotions, ESM, Human factors, Smartphone usage",
author = "Wataru Sasaki and Jin Nakazawa and Tadashi Okoshi",
year = "2018",
month = "10",
day = "8",
doi = "10.1145/3267305.3267699",
language = "English",
pages = "722--725",
booktitle = "UbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Comparing ESM timings for emotional estimation model with fine temporal granularity

AU - Sasaki, Wataru

AU - Nakazawa, Jin

AU - Okoshi, Tadashi

PY - 2018/10/8

Y1 - 2018/10/8

N2 - Towards wellbeing-awareness in computing, researches for estimating users' emotions using smartphone sensor data have been actively conducted as smartphones are getting more and more ubiquitous. Most studies have constructed emotion estimation models based on machine learning with contextual data from the smartphones and user's self-reporting ground truth label often collected via Experience Sampling Method (ESM). However, snice our emotion changes frequently in our daily lives, trying to collect the ground truth of such volatile emotions leads a storm of ESMs which could be burden to the users. In order to find better ESM methods, we propose and compare 3 ESMs, namely Randomized ESM that executes in randomly timings, Trigger ESM that executes when the user's behavior changes, and Unlocking ESM that sets up ESM on the unlocking screen. We constructed various emotional estimation models with four types of time granularity (1 day, 1/3 day, 3 hours, 1 hour) in four weeks experience with eight persons. As for the response rate, Unlocking ESM was the highest. In addition, it was clear that Unlocking ESM had the highest estimation accuracy in most cases.

AB - Towards wellbeing-awareness in computing, researches for estimating users' emotions using smartphone sensor data have been actively conducted as smartphones are getting more and more ubiquitous. Most studies have constructed emotion estimation models based on machine learning with contextual data from the smartphones and user's self-reporting ground truth label often collected via Experience Sampling Method (ESM). However, snice our emotion changes frequently in our daily lives, trying to collect the ground truth of such volatile emotions leads a storm of ESMs which could be burden to the users. In order to find better ESM methods, we propose and compare 3 ESMs, namely Randomized ESM that executes in randomly timings, Trigger ESM that executes when the user's behavior changes, and Unlocking ESM that sets up ESM on the unlocking screen. We constructed various emotional estimation models with four types of time granularity (1 day, 1/3 day, 3 hours, 1 hour) in four weeks experience with eight persons. As for the response rate, Unlocking ESM was the highest. In addition, it was clear that Unlocking ESM had the highest estimation accuracy in most cases.

KW - Affective computing

KW - Emotions

KW - ESM

KW - Human factors

KW - Smartphone usage

UR - http://www.scopus.com/inward/record.url?scp=85058290673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058290673&partnerID=8YFLogxK

U2 - 10.1145/3267305.3267699

DO - 10.1145/3267305.3267699

M3 - Conference contribution

SP - 722

EP - 725

BT - UbiComp/ISWC 2018 - Adjunct Proceedings of the 2018 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2018 ACM International Symposium on Wearable Computers

PB - Association for Computing Machinery, Inc

ER -