2021/03/05 by A. Sutherland, Alexander Sutherland, S. Magg +9
Computer Science · Psychology · #Artificial intelligence #Composition (language) #Computer science #Emotion and Mood Recognition #Emotion recognition #FOS: Computer and information sciences #Generalization #Linguistics #Machine Learning (cs.LG) #Modalities #Natural language processing #Sentiment Analysis and Opinion Mining #Speech Recognition and Synthesis #cs.LG
paper · pdf · doi:10.48550/arxiv.2103.03700
2 pages, 2 figures, presented at IROS 2018 Workshop on Language and Robotics
arxiv created 2021/03/05 · openalex publication_date 2021/03/05 · arxiv updated 2021/03/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Recognizing emotions from text in multimodal architectures has yielded promising results, surpassing video and audio modalities under certain circumstances. However, the method by which multimodal data is collected can be significant for recognizing emotional features in language. In this paper, we address the influence data collection methodology has on two multimodal emotion recognition datasets, the IEMOCAP dataset and the OMG-Emotion Behavior dataset, by analyzing textual dataset compositions and emotion recognition accuracy. Experiments with the full IEMOCAP dataset indicate that the composition negatively influences generalization performance when compared to the OMG-Emotion Behavior dataset. We conclude by discussing the impact this may have on HRI experiments.