Measuring Human Emotion in Short Documents to Improve Social Robot and Agent Interactions

Publication Type:
Conference Proceeding
ADCAIJ : Advances in Distributed Computing and Artificial Intelligence Journal, 2019, 11489 LNAI, pp. 29-41
Issue Date:
Filename Description Size
Skillicorn2019_Chapter_MeasuringHumanEmotionInShortDo.pdfPublished version582.89 kB
Adobe PDF
Full metadata record
© 2019, Springer Nature Switzerland AG. Social robots and agents can interact with people better if they can infer their affective state (emotions). While they cannot yet recognise affective state from tone and body language, they can use the fragments of speech that they (over)hear. We show that emotions – as conventionally framed – are difficult to detect. We suggest, from empirical results, that this is because emotions are the wrong granularity; and that emotions contain subemotions that are much more clearly separated from one another, and so are both easier to detect and to exploit.
Please use this identifier to cite or link to this item: