Cross-Domain Sentiment Classification using Vector Embedded Domain Representations

Nicolaj Filrup Rasmussen, Kristian Nørgaard Jensen, Marco Placenti, Thai Wang


Abstract
Due to the differences between reviews in different product categories, creating a general model for cross-domain sentiment classification can be a difficult task. This paper proposes an architecture that incorporates domain knowledge into a neural sentiment classification model. In addition to providing a cross-domain model, this also provides a quantifiable representation of the domains as numeric vectors. We show that it is possible to cluster the domain vectors and provide qualitative insights into the inter-domain relations. We also a) present a new data set for sentiment classification that includes a domain parameter and preprocessed data points, and b) perform an ablation study in order to determine whether some word groups impact performance.
Anthology ID:
W19-6206
Volume:
Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing
Month:
September
Year:
2019
Address:
Turku, Finland
Editors:
Joakim Nivre, Leon Derczynski, Filip Ginter, Bjørn Lindi, Stephan Oepen, Anders Søgaard, Jörg Tidemann
Venue:
NoDaLiDa
SIG:
Publisher:
Linköping University Electronic Press
Note:
Pages:
48–57
Language:
URL:
https://aclanthology.org/W19-6206
DOI:
Bibkey:
Cite (ACL):
Nicolaj Filrup Rasmussen, Kristian Nørgaard Jensen, Marco Placenti, and Thai Wang. 2019. Cross-Domain Sentiment Classification using Vector Embedded Domain Representations. In Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing, pages 48–57, Turku, Finland. Linköping University Electronic Press.
Cite (Informal):
Cross-Domain Sentiment Classification using Vector Embedded Domain Representations (Rasmussen et al., NoDaLiDa 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/W19-6206.pdf