Didn't you see my message? Predicting attentiveness to mobile instant messages

Martin Pielot, Rodrigo De Oliveira, Haewoon Kwak, Nuria Oliver

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

75 Citations (Scopus)

Abstract

Mobile instant messaging (e.g., via SMS or WhatsApp) often goes along with an expectation of high attentive- ness, i.e., that the receiver will notice and read the message within a few minutes. Hence, existing instant messaging services for mobile phones share indicators of availability, such as the last time the user has been on- line. However, in this paper we not only provide ev- idence that these cues create social pressure, but that they are also weak predictors of attentiveness. As rem- edy, we propose to share a machine-computed prediction of whether the user will view a message within the next few minutes or not. For two weeks, we collected behav- ioral data from 24 users of mobile instant messaging ser- vices. By the means of machine-learning techniques, we identi-ed that simple features extracted from the phone, such as the user's interaction with the noti-cation center, the screen activity, the proximity sensor, and the ringer mode, are strong predictors of how quickly the user will attend to the messages. With seven automatically se- lected features our model predicts whether a phone user will view a message within a few minutes with 70.6% accuracy and a precision for fast attendance of 81:2%.

Original languageEnglish
Title of host publicationConference on Human Factors in Computing Systems - Proceedings
PublisherAssociation for Computing Machinery
Pages3319-3328
Number of pages10
ISBN (Print)9781450324731
DOIs
Publication statusPublished - 1 Jan 2014
Externally publishedYes
Event32nd Annual ACM Conference on Human Factors in Computing Systems, CHI 2014 - Toronto, ON, Canada
Duration: 26 Apr 20141 May 2014

Other

Other32nd Annual ACM Conference on Human Factors in Computing Systems, CHI 2014
CountryCanada
CityToronto, ON
Period26/4/141/5/14

Fingerprint

Proximity sensors
Mobile phones
Learning systems
Positive ions
Availability

Keywords

  • Asynchronous Communication
  • Attentiveness
  • Availability
  • Messaging
  • Mobile Devices
  • Prediction

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Pielot, M., De Oliveira, R., Kwak, H., & Oliver, N. (2014). Didn't you see my message? Predicting attentiveness to mobile instant messages. In Conference on Human Factors in Computing Systems - Proceedings (pp. 3319-3328). Association for Computing Machinery. https://doi.org/10.1145/2556288.2556973

Didn't you see my message? Predicting attentiveness to mobile instant messages. / Pielot, Martin; De Oliveira, Rodrigo; Kwak, Haewoon; Oliver, Nuria.

Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery, 2014. p. 3319-3328.

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

Pielot, M, De Oliveira, R, Kwak, H & Oliver, N 2014, Didn't you see my message? Predicting attentiveness to mobile instant messages. in Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery, pp. 3319-3328, 32nd Annual ACM Conference on Human Factors in Computing Systems, CHI 2014, Toronto, ON, Canada, 26/4/14. https://doi.org/10.1145/2556288.2556973
Pielot M, De Oliveira R, Kwak H, Oliver N. Didn't you see my message? Predicting attentiveness to mobile instant messages. In Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery. 2014. p. 3319-3328 https://doi.org/10.1145/2556288.2556973
Pielot, Martin ; De Oliveira, Rodrigo ; Kwak, Haewoon ; Oliver, Nuria. / Didn't you see my message? Predicting attentiveness to mobile instant messages. Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery, 2014. pp. 3319-3328
@inproceedings{f2cf2d2fe54b42dea890628778db6456,
title = "Didn't you see my message? Predicting attentiveness to mobile instant messages",
abstract = "Mobile instant messaging (e.g., via SMS or WhatsApp) often goes along with an expectation of high attentive- ness, i.e., that the receiver will notice and read the message within a few minutes. Hence, existing instant messaging services for mobile phones share indicators of availability, such as the last time the user has been on- line. However, in this paper we not only provide ev- idence that these cues create social pressure, but that they are also weak predictors of attentiveness. As rem- edy, we propose to share a machine-computed prediction of whether the user will view a message within the next few minutes or not. For two weeks, we collected behav- ioral data from 24 users of mobile instant messaging ser- vices. By the means of machine-learning techniques, we identi-ed that simple features extracted from the phone, such as the user's interaction with the noti-cation center, the screen activity, the proximity sensor, and the ringer mode, are strong predictors of how quickly the user will attend to the messages. With seven automatically se- lected features our model predicts whether a phone user will view a message within a few minutes with 70.6{\%} accuracy and a precision for fast attendance of 81:2{\%}.",
keywords = "Asynchronous Communication, Attentiveness, Availability, Messaging, Mobile Devices, Prediction",
author = "Martin Pielot and {De Oliveira}, Rodrigo and Haewoon Kwak and Nuria Oliver",
year = "2014",
month = "1",
day = "1",
doi = "10.1145/2556288.2556973",
language = "English",
isbn = "9781450324731",
pages = "3319--3328",
booktitle = "Conference on Human Factors in Computing Systems - Proceedings",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Didn't you see my message? Predicting attentiveness to mobile instant messages

AU - Pielot, Martin

AU - De Oliveira, Rodrigo

AU - Kwak, Haewoon

AU - Oliver, Nuria

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Mobile instant messaging (e.g., via SMS or WhatsApp) often goes along with an expectation of high attentive- ness, i.e., that the receiver will notice and read the message within a few minutes. Hence, existing instant messaging services for mobile phones share indicators of availability, such as the last time the user has been on- line. However, in this paper we not only provide ev- idence that these cues create social pressure, but that they are also weak predictors of attentiveness. As rem- edy, we propose to share a machine-computed prediction of whether the user will view a message within the next few minutes or not. For two weeks, we collected behav- ioral data from 24 users of mobile instant messaging ser- vices. By the means of machine-learning techniques, we identi-ed that simple features extracted from the phone, such as the user's interaction with the noti-cation center, the screen activity, the proximity sensor, and the ringer mode, are strong predictors of how quickly the user will attend to the messages. With seven automatically se- lected features our model predicts whether a phone user will view a message within a few minutes with 70.6% accuracy and a precision for fast attendance of 81:2%.

AB - Mobile instant messaging (e.g., via SMS or WhatsApp) often goes along with an expectation of high attentive- ness, i.e., that the receiver will notice and read the message within a few minutes. Hence, existing instant messaging services for mobile phones share indicators of availability, such as the last time the user has been on- line. However, in this paper we not only provide ev- idence that these cues create social pressure, but that they are also weak predictors of attentiveness. As rem- edy, we propose to share a machine-computed prediction of whether the user will view a message within the next few minutes or not. For two weeks, we collected behav- ioral data from 24 users of mobile instant messaging ser- vices. By the means of machine-learning techniques, we identi-ed that simple features extracted from the phone, such as the user's interaction with the noti-cation center, the screen activity, the proximity sensor, and the ringer mode, are strong predictors of how quickly the user will attend to the messages. With seven automatically se- lected features our model predicts whether a phone user will view a message within a few minutes with 70.6% accuracy and a precision for fast attendance of 81:2%.

KW - Asynchronous Communication

KW - Attentiveness

KW - Availability

KW - Messaging

KW - Mobile Devices

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=84900417167&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900417167&partnerID=8YFLogxK

U2 - 10.1145/2556288.2556973

DO - 10.1145/2556288.2556973

M3 - Conference contribution

SN - 9781450324731

SP - 3319

EP - 3328

BT - Conference on Human Factors in Computing Systems - Proceedings

PB - Association for Computing Machinery

ER -