From Speaker Identification to Affective Analysis: A Multi-Step System for Analyzing Children's Stories
Elias Iosif, Taniya Mishra · 2014
We propose a multi-step system for the analysis of children’s stories that is in-tended to be part of a larger text-to-speech-based storytelling system. A hybrid ap-proach is adopted, where pattern-based and statistical methods are used along with utilization of external knowledge sources. This system performs the following story analysis tasks: identification of charac-ters in each story; attribution of quotes to specific story characters; identification of character age, gender and other salient personality attributes; and finally, affective analysis of the quoted material. The differ-ent types of analyses were evaluated using several datasets. For the quote attribution, as well as for the gender and age estima-tion, substantial improvement over base-line was realized, whereas results for per-sonality attribute estimation and valence estimation are more modest. 1