of Natural Language Scripts

Abstract Performing plays or creating films and animations is a complex creative, and thus expensive process, involving various professionals and media. This paper re-views artificial intelligence text-to-animation systems and tools to augment this process by automatically interpreting film and play scripts and automatically generating an-imated scenes. Special attention is given to emotional aspects and their reflection in the execution of all types of modalities during the generation of the story content. Systems detect explicit emotion keywords from the story script or infer emotions from the story context with various methods. Emotional aspects affect fluency and manner of actions and behaviour, body language, facial expressions, speech, scene composition, timing, lighting, music and camera. The main objective of this work is to demonstrate how a scene and actor behaviour changes when emotional states are taken into ac-count, e.g. walking down a street in a happy versus a sad state. Consequently, more realistic and believable story visualisations are achieved. Literature on related research areas is reviewed involving natural language and text, screenplay or play script, lay-out processing with regard to personality and emotion detection, affective reasonin