基于情感分布的emoji嵌入式表示

Emoji embedded representation based on emotion distribution

提出了一种基于情感分布的emoji嵌入式表示方法(emoji embedded representation based on emotion distribution,EDEER)。EDEER方法采用基于BERT的情绪预测模型软标签,从真实数据中学习emoji嵌入式表示,通过情感分布直接建模emoji在各种情绪上的表达程度,使嵌入式表示中包含emoji的多种情感信息。在包含emoji的中文微博数据集上的多组对比实验表明,本文提出的方法可以有效地学习到与细粒度情绪直接关联的emoji嵌入式表示,构建具有较高情绪表达质量的emoji表示空间。

This paper proposes an emoji embedded representation based on emotion distribution(EDEER)method.The EDEER method adopts the soft label of BERT-based emotion prediction model to learn emoji embedded representation from real data,and directly models the expression degree of emoji on various sentiments through emotion distribution,so that the embedded representation contains various emotional information of emoji.Multiple sets of comparative experiments on the Chinese Weibo dataset containing emoji shows that the method proposed in this paper can effectively learn emoji embedded representations that are directly related to fine-grained sentiments,and build an emoji representation space with high emotional expression quality.