Super Characters: A Conversion from Sentiment Classification to Image Classification

Baohua Sun, Lin Yang, Patrick Dong, Wenhan Zhang, Jason Dong, Charles Young


Abstract
We propose a method named Super Characters for sentiment classification. This method converts the sentiment classification problem into image classification problem by projecting texts into images and then applying CNN models for classification. Text features are extracted automatically from the generated Super Characters images, hence there is no need of any explicit step of embedding the words or characters into numerical vector representations. Experimental results on large social media corpus show that the Super Characters method consistently outperforms other methods for sentiment classification and topic classification tasks on ten large social media datasets of millions of contents in four different languages, including Chinese, Japanese, Korean and English.
Anthology ID:
W18-6245
Volume:
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Alexandra Balahur, Saif M. Mohammad, Veronique Hoste, Roman Klinger
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
309–315
Language:
URL:
https://aclanthology.org/W18-6245
DOI:
10.18653/v1/W18-6245
Bibkey:
Cite (ACL):
Baohua Sun, Lin Yang, Patrick Dong, Wenhan Zhang, Jason Dong, and Charles Young. 2018. Super Characters: A Conversion from Sentiment Classification to Image Classification. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 309–315, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Super Characters: A Conversion from Sentiment Classification to Image Classification (Sun et al., WASSA 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6245.pdf