A necessary step in the generation of expressive speech synthesis is the automatic detection and classification of emotions most likely to be present in textual input. We have recently advocated  a new emotion analysis strategy leveraging two separate semantic levels: one that encapsulates the foundations of the domain considered, and one that specifically accounts for the overall affective fabric of the language. This paper expands this premise into a more general framework, dubbed latent affective mapping, to expose the emergent relationship between these two levels. Such connection in turn advantageously informs the emotion classification process. The benefits gained though a richer description of the underlying affective space are illustrated via an empirical comparison of two different mapping instantiations (latent affective folding and latent affective embedding) with more conventional techniques based on expert knowledge of emotional keywords and keysets.
Bibliographic reference. Bellegarda, Jerome R. (2010): "Latent affective mapping: a novel framework for the data-driven analysis of emotion in text", In INTERSPEECH-2010, 1117-1120.