Annotating Errors and Emotions in Human-Chatbot Interactions in Italian

Manuela Sanguinetti, Alessandro Mazzei, Viviana Patti, Marco Scalerandi, Dario Mana, Rossana Simeoni


Abstract
This paper describes a novel annotation scheme specifically designed for a customer-service context where written interactions take place between a given user and the chatbot of an Italian telecommunication company. More specifically, the scheme aims to detect and highlight two aspects: the presence of errors in the conversation on both sides (i.e. customer and chatbot) and the “emotional load” of the conversation. This can be inferred from the presence of emotions of some kind (especially negative ones) in the customer messages, and from the possible empathic responses provided by the agent. The dataset annotated according to this scheme is currently used to develop the prototype of a rule-based Natural Language Generation system aimed at improving the chatbot responses and the customer experience overall.
Anthology ID:
2020.law-1.14
Volume:
Proceedings of the 14th Linguistic Annotation Workshop
Month:
December
Year:
2020
Address:
Barcelona, Spain
Venues:
COLING | LAW
SIG:
SIGANN
Publisher:
Association for Computational Linguistics
Note:
Pages:
148–159
Language:
URL:
https://aclanthology.org/2020.law-1.14
DOI:
Bibkey:
Cite (ACL):
Manuela Sanguinetti, Alessandro Mazzei, Viviana Patti, Marco Scalerandi, Dario Mana, and Rossana Simeoni. 2020. Annotating Errors and Emotions in Human-Chatbot Interactions in Italian. In Proceedings of the 14th Linguistic Annotation Workshop, pages 148–159, Barcelona, Spain. Association for Computational Linguistics.
Cite (Informal):
Annotating Errors and Emotions in Human-Chatbot Interactions in Italian (Sanguinetti et al., LAW 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.law-1.14.pdf