Super Characters: A Conversion from Sentiment Classification to Image Classification

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.

arXiv comment7 pages, 1 figure, 5 tables. Accepted by EMNLP2018 workshop WASSA2018

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Convolutional Neural Networks for Sentence Classification
• Text Understanding from Scratch
• Learning Chinese Word Representations From Glyphs Of Characters

Cited by in corpus (3)

• Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis
• Word Shape Matters: Robust Machine Translation with Visual Embedding
• An Investigation of Transfer Learning-Based Sentiment Analysis in Japanese