Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Affective Content Classification using Convolutional Neural Networks

: Claeser, Daniel

Fulltext (PDF; )

Chhaya, N.:
2nd Workshop on Affective Content Analysis, AffCon 2019. Proceedings. Online resource : Co-located with Thirty-Third AAAI Conference on Artificial Intelligence AAAI 2019, Honolulu, USA, January 27, 2019
Honolulu/Hawaii, 2019 (CEUR Workshop Proceedings 2328)
Workshop on Affective Content Analysis (AffCon) <2, 2019, Honolulu/Hawaii>
Conference on Artificial Intelligence (AAAI) <33, 2019, Honolulu/Hawaii>
Conference Paper, Electronic Publication
Fraunhofer FKIE ()

We present a three-layer convolutional neural network for the classification of two binary target variables 'Social' and 'Agency' in the HappyDB corpus exploiting lexical density of a closed domain and a high degree of regularity in linguistic patterns. Incorporating demographic information is demonstrated to improve classification accuracy. Custom embeddings learned from additional unlabeled data perform competitive to established pre-trained models based on much more comprehensive general training corpora. The top-performing model achieves accuracies of 0.90 for the 'Social' and 0.875 for the 'Agency' variable.