Towards a Visual Analytics System for Emotion Trajectories in Multiparty Conversations
Loading...
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Visualizing sentiments in textual data has received growing interest; however, representing emotions within interlocutor relationships and associating them with the temporal progression of dialogues remains challenging. In this poster abstract, we describe the ongoing work on a visual analytics tool designed for analyzing emotion trajectories within dialogue collections composed of utterances from multiple speakers. The proposed tool provides exploration at different levels of detail to complex multigraphs, where edges represent direct responses between speakers through their utterances. Our approach includes several selection strategies for connecting different views: summaries of emotion transitions across dialogue groups, detailed analyses of individual utterances within specific dialogues of interest in interlocutor networks, and close reading. The tool aims to support model development in natural language processing by allowing users to explore text corpora interactively.
Description
CCS Concepts: Human-centered computing→Visual analytics
@inproceedings{10.2312:evp.20241092,
booktitle = {EuroVis 2024 - Posters},
editor = {Kucher, Kostiantyn and Diehl, Alexandra and Gillmann, Christina},
title = {{Towards a Visual Analytics System for Emotion Trajectories in Multiparty Conversations}},
author = {Huang, Zeyang and Kucher, Kostiantyn and Kerren, Andreas},
year = {2024},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-258-5},
DOI = {10.2312/evp.20241092}
}