Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Adapting established text representations for predicting review sentiment in Turkish

: Çavuşoğlu, I.; Pielka, M.; Sifa, R.


Webb, G. ; Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
IEEE 7th International Conference on Data Science and Advanced Analytics, DSAA 2020. Proceedings : 6-9 October 2020, Sydney, Australia
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2020
ISBN: 978-1-7281-8206-3
ISBN: 978-1-7281-8207-0
International Conference on Data Science and Advanced Analytics (DSAA) <7, 2020, Online>
Fraunhofer IAIS ()

Natural Language Processing, and specifically Sentiment Analysis are still unexplored topics with respect to Turkish text. A key challenge is to extract meaningful word and paragraph representations. We provide a comprehensive overview on pre-processing and featurization methods for this problem. Our focus is on the inherent difficulties that come with analyzing Turkish real-world data from the e-commerce domain, such as inconsistent spelling or complicated morphological and grammatical structures.