INTERSPEECH 2011 12th Annual Conference of the International Speech Communication Association Florence, Italy August 27-31. 2011

Kernel Models for Affective Lexicon Creation

Nikos Malandrakis (1), Alexandros Potamianos (1), Elias Iosif (1), Shrikanth Narayanan (2)

(1) Technical University of Crete, Greece
(2) University of Southern California, USA

Emotion recognition algorithms for spoken dialogue applications typically employ lexical models that are trained on labeled indomain data. In this paper, we propose a domain-independent approach to affective text modeling that is based on the creation of an affective lexicon. Starting from a small set of manually annotated seed words, continuous valence ratings for new words are estimated using semantic similarity scores and a kernel model. The parameters of the model are trained using least mean squares estimation. Word level scores are combined to produce sentencelevel scores via simple linear and non-linear fusion. The proposed method is evaluated on the SemEval news headline polarity task and on the ChIMP politeness and frustration detection dialogue task, achieving state-of-the-art results on both. For politeness detection, best results are obtained when the affective model is adapted using in domain data. For frustration detection, the domain-independent model and non-linear fusion achieve the best performance.

Full Paper

Bibliographic reference.  Malandrakis, Nikos / Potamianos, Alexandros / Iosif, Elias / Narayanan, Shrikanth (2011): "Kernel models for affective lexicon creation", In INTERSPEECH-2011, 2977-2980.