Multi-level analysis and recognition of the text sentiment on the example of consumer opinions

Jan Kocoń, Monika Zaśko-Zielińska, Piotr Miłkowski


Abstract
In this article, we present a novel multi-domain dataset of Polish text reviews, annotated with sentiment on different levels: sentences and the whole documents. The annotation was made by linguists in a 2+1 scheme (with inter-annotator agreement analysis). We present a preliminary approach to the classification of labelled data using logistic regression, bidirectional long short-term memory recurrent neural networks (BiLSTM) and bidirectional encoder representations from transformers (BERT).
Anthology ID:
R19-1066
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
559–567
Language:
URL:
https://aclanthology.org/R19-1066
DOI:
10.26615/978-954-452-056-4_066
Bibkey:
Cite (ACL):
Jan Kocoń, Monika Zaśko-Zielińska, and Piotr Miłkowski. 2019. Multi-level analysis and recognition of the text sentiment on the example of consumer opinions. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 559–567, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Multi-level analysis and recognition of the text sentiment on the example of consumer opinions (Kocoń et al., RANLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/R19-1066.pdf