FlowDisco: Interactive Exploration of Dialogue Flows

Patrícia Ferreira, Carolina Loureiro, Ana Alves, Catarina Silva, Hugo Gonçalo Oliveira


Abstract
Analyzing large conversational datasets is often inefficient due to the linear nature of text, which hinders the tracking of interaction evolution over time. To address this, we present FlowDisco, an interactive platform for the automatic discovery and exploration of dialogue flows. The framework uses semantic embeddings and modular clustering to transform raw text into probabilistic dialogue flows. By providing a web interface with dynamic filtering and a suite of analytical metrics, FlowDisco simplifies the visual identification and validation of conversational behaviors at scale. The platform’s utility is demonstrated through real-world application scenarios, including customer support interactions and multi-party political debates, where it successfully uncovers complex patterns and sentiment shifts that traditional sequential analysis often overlooks.
Anthology ID:
2026.propor-2.5
Volume:
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2
Month:
April
Year:
2026
Address:
Salvador, Brazil
Editors:
Marlo Souza, Iria de-Dios-Flores, Diana Santos, Larissa Freitas, Jackson Wilke da Cruz Souza, Eugénio Ribeiro
Venue:
PROPOR
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14–17
Language:
URL:
https://aclanthology.org/2026.propor-2.5/
DOI:
Bibkey:
Cite (ACL):
Patrícia Ferreira, Carolina Loureiro, Ana Alves, Catarina Silva, and Hugo Gonçalo Oliveira. 2026. FlowDisco: Interactive Exploration of Dialogue Flows. In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2, pages 14–17, Salvador, Brazil. Association for Computational Linguistics.
Cite (Informal):
FlowDisco: Interactive Exploration of Dialogue Flows (Ferreira et al., PROPOR 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.propor-2.5.pdf