Towards an Online Emotional Support Agent: Identifying Emotional Support Strategies via Crowdsourcing (2-page Extended Abstract)

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

Abstract

In this paper, an empirical study conducted with Amazon Mechanical
Turk workers is presented that aims to make a correspondence
between messages about stressful situations, which were shared via
Twitter, and 5 different types of supportive replies to them. Around
10.00 tweets were collected and analyzed in the terms previously
described. We performed statistical tests to determine possible correlations
between causes of stress and supportive response strategies.
We are about to use these findings to improve a previously
implemented algorithm that automatically generates supportive
messages to stressed users. This algorithm is the core of an agent,
in the form of a chatbot, that would be able to interact with such
stressed users as if it would belong to their social networks.
LanguageEnglish
Title of host publicationProceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS'18
PublisherACM Press
Pages2242-2244
Number of pages3
ISBN (Print)9781450356497
StatePublished - 2018
EventAAMAS 2018 Conference : July 10-15, 2018 Stockholm - Stockholm, Sweden
Duration: 10 Jul 201815 Jul 2018
http://www.ifaamas.org/AAMAS/aamas2018/

Publication series

NameAAMAS Conference proceedings.
PublisherIFAAMAS
Volume17th
ISSN (Print)2523-5699

Conference

ConferenceAAMAS 2018 Conference : July 10-15, 2018 Stockholm
CountrySweden
CityStockholm
Period10/07/1815/07/18
Internet address

Fingerprint

Statistical tests

Cite this

Medeiros, L., & Bosse, T. (2018). Towards an Online Emotional Support Agent: Identifying Emotional Support Strategies via Crowdsourcing (2-page Extended Abstract). In Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS'18 (pp. 2242-2244). (AAMAS Conference proceedings.; Vol. 17th). ACM Press.
Medeiros, L. ; Bosse, Tibor. / Towards an Online Emotional Support Agent: Identifying Emotional Support Strategies via Crowdsourcing (2-page Extended Abstract). Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS'18. ACM Press, 2018. pp. 2242-2244 (AAMAS Conference proceedings.).
@inproceedings{ed3ab47a25fa4b34aeccebc57f9024de,
title = "Towards an Online Emotional Support Agent: Identifying Emotional Support Strategies via Crowdsourcing (2-page Extended Abstract)",
abstract = "In this paper, an empirical study conducted with Amazon MechanicalTurk workers is presented that aims to make a correspondencebetween messages about stressful situations, which were shared viaTwitter, and 5 different types of supportive replies to them. Around10.00 tweets were collected and analyzed in the terms previouslydescribed. We performed statistical tests to determine possible correlationsbetween causes of stress and supportive response strategies.We are about to use these findings to improve a previouslyimplemented algorithm that automatically generates supportivemessages to stressed users. This algorithm is the core of an agent,in the form of a chatbot, that would be able to interact with suchstressed users as if it would belong to their social networks.",
author = "L. Medeiros and Tibor Bosse",
year = "2018",
language = "English",
isbn = "9781450356497",
series = "AAMAS Conference proceedings.",
publisher = "ACM Press",
pages = "2242--2244",
booktitle = "Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS'18",

}

Medeiros, L & Bosse, T 2018, Towards an Online Emotional Support Agent: Identifying Emotional Support Strategies via Crowdsourcing (2-page Extended Abstract). in Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS'18. AAMAS Conference proceedings., vol. 17th, ACM Press, pp. 2242-2244, AAMAS 2018 Conference : July 10-15, 2018 Stockholm, Stockholm, Sweden, 10/07/18.

Towards an Online Emotional Support Agent: Identifying Emotional Support Strategies via Crowdsourcing (2-page Extended Abstract). / Medeiros, L.; Bosse, Tibor.

Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS'18. ACM Press, 2018. p. 2242-2244 (AAMAS Conference proceedings.; Vol. 17th).

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

TY - GEN

T1 - Towards an Online Emotional Support Agent: Identifying Emotional Support Strategies via Crowdsourcing (2-page Extended Abstract)

AU - Medeiros,L.

AU - Bosse,Tibor

PY - 2018

Y1 - 2018

N2 - In this paper, an empirical study conducted with Amazon MechanicalTurk workers is presented that aims to make a correspondencebetween messages about stressful situations, which were shared viaTwitter, and 5 different types of supportive replies to them. Around10.00 tweets were collected and analyzed in the terms previouslydescribed. We performed statistical tests to determine possible correlationsbetween causes of stress and supportive response strategies.We are about to use these findings to improve a previouslyimplemented algorithm that automatically generates supportivemessages to stressed users. This algorithm is the core of an agent,in the form of a chatbot, that would be able to interact with suchstressed users as if it would belong to their social networks.

AB - In this paper, an empirical study conducted with Amazon MechanicalTurk workers is presented that aims to make a correspondencebetween messages about stressful situations, which were shared viaTwitter, and 5 different types of supportive replies to them. Around10.00 tweets were collected and analyzed in the terms previouslydescribed. We performed statistical tests to determine possible correlationsbetween causes of stress and supportive response strategies.We are about to use these findings to improve a previouslyimplemented algorithm that automatically generates supportivemessages to stressed users. This algorithm is the core of an agent,in the form of a chatbot, that would be able to interact with suchstressed users as if it would belong to their social networks.

UR - http://ifaamas.org/Proceedings/aamas2018/

M3 - Conference contribution

SN - 9781450356497

T3 - AAMAS Conference proceedings.

SP - 2242

EP - 2244

BT - Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS'18

PB - ACM Press

ER -

Medeiros L, Bosse T. Towards an Online Emotional Support Agent: Identifying Emotional Support Strategies via Crowdsourcing (2-page Extended Abstract). In Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS'18. ACM Press. 2018. p. 2242-2244. (AAMAS Conference proceedings.).