A privacy-preserving dialogue system based on argumentation
Dialogue systems are a class of increasingly popular AI-based solutions to support timely and interactive communication with users in many domains. Due to the apparent possibility of users disclosing their sensitive data when interacting with such systems, ensuring that the systems follow the releva...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Intelligent Systems with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667305322000515 |
| _version_ | 1818494099178651648 |
|---|---|
| author | Bettina Fazzinga Andrea Galassi Paolo Torroni |
| author_facet | Bettina Fazzinga Andrea Galassi Paolo Torroni |
| author_sort | Bettina Fazzinga |
| collection | DOAJ |
| description | Dialogue systems are a class of increasingly popular AI-based solutions to support timely and interactive communication with users in many domains. Due to the apparent possibility of users disclosing their sensitive data when interacting with such systems, ensuring that the systems follow the relevant laws, regulations, and ethical principles should be of primary concern. In this context, we discuss the main open points regarding these aspects and propose an approach grounded on a computational argumentation framework. Our approach ensures that user data are managed according to data minimization, purpose limitation, and integrity. Moreover, it is endowed with the capability of providing motivations for the system responses to offer transparency and explainability. We illustrate the architecture using as a case study a COVID-19 vaccine information system, discuss its theoretical properties, and evaluate it empirically. |
| first_indexed | 2024-12-10T18:02:15Z |
| format | Article |
| id | doaj.art-81ac70f24e544ebdba9598a9f2e6d52d |
| institution | Directory Open Access Journal |
| issn | 2667-3053 |
| language | English |
| last_indexed | 2024-12-10T18:02:15Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Intelligent Systems with Applications |
| spelling | doaj.art-81ac70f24e544ebdba9598a9f2e6d52d2022-12-22T01:38:44ZengElsevierIntelligent Systems with Applications2667-30532022-11-0116200113A privacy-preserving dialogue system based on argumentationBettina Fazzinga0Andrea Galassi1Paolo Torroni2DICES, University of Calabria, Via Pietro Bucci, Rende, 87036, ItalyCorresponding author.; DISI, University of Bologna, Viale Risorgimento 2, Bologna, 40136, ItalyDISI, University of Bologna, Viale Risorgimento 2, Bologna, 40136, ItalyDialogue systems are a class of increasingly popular AI-based solutions to support timely and interactive communication with users in many domains. Due to the apparent possibility of users disclosing their sensitive data when interacting with such systems, ensuring that the systems follow the relevant laws, regulations, and ethical principles should be of primary concern. In this context, we discuss the main open points regarding these aspects and propose an approach grounded on a computational argumentation framework. Our approach ensures that user data are managed according to data minimization, purpose limitation, and integrity. Moreover, it is endowed with the capability of providing motivations for the system responses to offer transparency and explainability. We illustrate the architecture using as a case study a COVID-19 vaccine information system, discuss its theoretical properties, and evaluate it empirically.http://www.sciencedirect.com/science/article/pii/S266730532200051568T5068T3568T99 |
| spellingShingle | Bettina Fazzinga Andrea Galassi Paolo Torroni A privacy-preserving dialogue system based on argumentation Intelligent Systems with Applications 68T50 68T35 68T99 |
| title | A privacy-preserving dialogue system based on argumentation |
| title_full | A privacy-preserving dialogue system based on argumentation |
| title_fullStr | A privacy-preserving dialogue system based on argumentation |
| title_full_unstemmed | A privacy-preserving dialogue system based on argumentation |
| title_short | A privacy-preserving dialogue system based on argumentation |
| title_sort | privacy preserving dialogue system based on argumentation |
| topic | 68T50 68T35 68T99 |
| url | http://www.sciencedirect.com/science/article/pii/S2667305322000515 |
| work_keys_str_mv | AT bettinafazzinga aprivacypreservingdialoguesystembasedonargumentation AT andreagalassi aprivacypreservingdialoguesystembasedonargumentation AT paolotorroni aprivacypreservingdialoguesystembasedonargumentation AT bettinafazzinga privacypreservingdialoguesystembasedonargumentation AT andreagalassi privacypreservingdialoguesystembasedonargumentation AT paolotorroni privacypreservingdialoguesystembasedonargumentation |