Publikationen

Fraunhofer SIT at WASSA 2024 Empathy and Personality Shared Task: Use of Sentiment Transformers and Data Augmentation With Fuzzy Labels to Predict Emotional Reactions in Conversations and Essays

AutorFrick, Raphael Antonius; Steinebach, Martin
Datum2024
ArtConference Paper
AbstraktPredicting emotions and emotional reactions during conversations and within texts poses challenges, even for advanced AI systems. The second iteration of the WASSA Empathy and Personality Shared Task focuses on creating innovative models that can anticipate emotional responses to news articles containing harmful content across four tasks. In this paper, we introduce our Fraunhofer SIT team’s solutions for the three tasks: Task 1 (CONVD), Task 2 (CONVT), and Task 3 (EMP). It involves combining LLM-driven data augmentation with fuzzy labels and fine-tuning RoBERTa models pre-trained on sentiment classification tasks to solve the regression problems. In the competition, our solutions achieved 1st place in Track 1 (CONV-dialog), 8th in Track 2 (CONV-turn), and 3rd place in Track 3 (EMP).
Konferenz14th Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis, WASSA 2024
ISBN9798891761568
Urlhttps://publica.fraunhofer.de/handle/publica/510222

Cyber­security-Konferenzen

zur Übersicht

Aus- und Weiterbildung

Informieren Sie sich über die Aus- und Weiter­bildungs­angebote der in ATHENE mitwirkenden Institutionen

Mehr INFO