Using crowdsourcing for the development of online emotional support agents

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

This paper describes several steps towards the development of an online agent (or socialbot) that provides emotional support to stressed users. In particular, we present an empirical study that was conducted with the aim to investigate how people help each other to cope with stressful situations via online social networks. To this end, around 10.000 tweets about stressful situations were collected. Then, using crowdsourcing, these tweets were classified into stress categories, and supportive replies to them were collected, which were also classified into categories. Contingency tables were constructed in order to explore which types of support were most frequently used in which circumstances. The resulting values can be used as parameters for a previously developed algorithm that automatically constructs support messages. This allows our agent to generate supportive messages that are more similar to the support messages that human beings send via social media.

LanguageEnglish
Title of host publicationHighlights of Practical Applications of Agents, Multi-Agent Systems, and Complexity
Subtitle of host publicationThe PAAMS Collection - International Workshops of PAAMS 2018, Proceedings
PublisherSpringer/Verlag
Pages196-209
Number of pages14
ISBN (Electronic)9783319947792
ISBN (Print)9783319947785
DOIs
StatePublished - 2018
Event16th International Conference on Practical Applications of Agents, Multi-Agent Systems, PAAMS 2018 - Toledo, Spain
Duration: 20 Jun 201822 Jun 2018

Publication series

NameCommunications in Computer and Information Science
Volume887
ISSN (Print)1865-0929

Conference

Conference16th International Conference on Practical Applications of Agents, Multi-Agent Systems, PAAMS 2018
CountrySpain
CityToledo
Period20/06/1822/06/18

Fingerprint

Social Media
Contingency Table
Empirical Study
Social Networks
Emotion
Human

Cite this

Medeiros, L., & Bosse, T. (2018). Using crowdsourcing for the development of online emotional support agents. In Highlights of Practical Applications of Agents, Multi-Agent Systems, and Complexity: The PAAMS Collection - International Workshops of PAAMS 2018, Proceedings (pp. 196-209). (Communications in Computer and Information Science; Vol. 887). Springer/Verlag. DOI: 10.1007/978-3-319-94779-2_18
Medeiros, Lenin ; Bosse, Tibor. / Using crowdsourcing for the development of online emotional support agents. Highlights of Practical Applications of Agents, Multi-Agent Systems, and Complexity: The PAAMS Collection - International Workshops of PAAMS 2018, Proceedings. Springer/Verlag, 2018. pp. 196-209 (Communications in Computer and Information Science).
@inproceedings{d11f8949bae04b408d3352d76eefd56f,
title = "Using crowdsourcing for the development of online emotional support agents",
abstract = "This paper describes several steps towards the development of an online agent (or socialbot) that provides emotional support to stressed users. In particular, we present an empirical study that was conducted with the aim to investigate how people help each other to cope with stressful situations via online social networks. To this end, around 10.000 tweets about stressful situations were collected. Then, using crowdsourcing, these tweets were classified into stress categories, and supportive replies to them were collected, which were also classified into categories. Contingency tables were constructed in order to explore which types of support were most frequently used in which circumstances. The resulting values can be used as parameters for a previously developed algorithm that automatically constructs support messages. This allows our agent to generate supportive messages that are more similar to the support messages that human beings send via social media.",
author = "Lenin Medeiros and Tibor Bosse",
year = "2018",
doi = "10.1007/978-3-319-94779-2_18",
language = "English",
isbn = "9783319947785",
series = "Communications in Computer and Information Science",
publisher = "Springer/Verlag",
pages = "196--209",
booktitle = "Highlights of Practical Applications of Agents, Multi-Agent Systems, and Complexity",

}

Medeiros, L & Bosse, T 2018, Using crowdsourcing for the development of online emotional support agents. in Highlights of Practical Applications of Agents, Multi-Agent Systems, and Complexity: The PAAMS Collection - International Workshops of PAAMS 2018, Proceedings. Communications in Computer and Information Science, vol. 887, Springer/Verlag, pp. 196-209, 16th International Conference on Practical Applications of Agents, Multi-Agent Systems, PAAMS 2018, Toledo, Spain, 20/06/18. DOI: 10.1007/978-3-319-94779-2_18

Using crowdsourcing for the development of online emotional support agents. / Medeiros, Lenin; Bosse, Tibor.

Highlights of Practical Applications of Agents, Multi-Agent Systems, and Complexity: The PAAMS Collection - International Workshops of PAAMS 2018, Proceedings. Springer/Verlag, 2018. p. 196-209 (Communications in Computer and Information Science; Vol. 887).

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Using crowdsourcing for the development of online emotional support agents

AU - Medeiros,Lenin

AU - Bosse,Tibor

PY - 2018

Y1 - 2018

N2 - This paper describes several steps towards the development of an online agent (or socialbot) that provides emotional support to stressed users. In particular, we present an empirical study that was conducted with the aim to investigate how people help each other to cope with stressful situations via online social networks. To this end, around 10.000 tweets about stressful situations were collected. Then, using crowdsourcing, these tweets were classified into stress categories, and supportive replies to them were collected, which were also classified into categories. Contingency tables were constructed in order to explore which types of support were most frequently used in which circumstances. The resulting values can be used as parameters for a previously developed algorithm that automatically constructs support messages. This allows our agent to generate supportive messages that are more similar to the support messages that human beings send via social media.

AB - This paper describes several steps towards the development of an online agent (or socialbot) that provides emotional support to stressed users. In particular, we present an empirical study that was conducted with the aim to investigate how people help each other to cope with stressful situations via online social networks. To this end, around 10.000 tweets about stressful situations were collected. Then, using crowdsourcing, these tweets were classified into stress categories, and supportive replies to them were collected, which were also classified into categories. Contingency tables were constructed in order to explore which types of support were most frequently used in which circumstances. The resulting values can be used as parameters for a previously developed algorithm that automatically constructs support messages. This allows our agent to generate supportive messages that are more similar to the support messages that human beings send via social media.

UR - http://www.scopus.com/inward/record.url?scp=85049379312&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049379312&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-94779-2_18

DO - 10.1007/978-3-319-94779-2_18

M3 - Conference contribution

SN - 9783319947785

T3 - Communications in Computer and Information Science

SP - 196

EP - 209

BT - Highlights of Practical Applications of Agents, Multi-Agent Systems, and Complexity

PB - Springer/Verlag

ER -

Medeiros L, Bosse T. Using crowdsourcing for the development of online emotional support agents. In Highlights of Practical Applications of Agents, Multi-Agent Systems, and Complexity: The PAAMS Collection - International Workshops of PAAMS 2018, Proceedings. Springer/Verlag. 2018. p. 196-209. (Communications in Computer and Information Science). Available from, DOI: 10.1007/978-3-319-94779-2_18