山西大学学报（自然科学版）2025，Vol.48Issue(5)：849-858,10.DOI:10.13451/j.sxu.ns.2025014
融合情感分布的多标签emoji预测模型
Emotion Distribution Enhanced Multi-label Emoji Prediction
摘要
Abstract
Emoji,as an effective tool for emotional expression,has been widely used in daily internet-based communication.Current-ly,most emoji prediction models employ word embedding methods to construct emoji representations,but consider neither the direct association between emoji and emotions,nor the co-occurrence patterns of emoji in the target dataset,resulting in insufficient emo-tional discriminability of the learned emoji representations.To address these issues,this paper proposes a multi-label emoji predic-tion model based on the emotional distribution of emojis directly related to emotion,which is named EIFEP(i.e.,Emotion distribu-tion Information Fusion for multi-label Emoji Prediction).The EIFEP model consists of three modules:a semantic information mod-ule,an emoji information module,and an information fusion prediction module.The semantic information module uses BERT to ex-tract text semantic representation;the emoji information module applies a multi-layer graph convolutional network to construct emo-ji embedding that integrate emotion distribution and co-occurrence pattern information;the information fusion prediction module us-es emoji embedding attention mechanism to integrate the text semantic and the emoji embedding matrix for emoji prediction.The comparative experiments on the Mu-Emoji English dataset demonstrate that the EIFEP model outperformers the existing multi-label emoji prediction model,achieving 60.88%in Acc,58.79%in JS,74.05%in micF1,and 6.92%in HL,respectively.关键词
Emoji预测/多标签分类/标签相关性/情感分析/图卷积网络Key words
emoji prediction/multi-label classification/label correlation/sentiment analysis/graph convolutional network分类
信息技术与安全科学引用本文复制引用
熊珠珠,刘仕鑫,万中英,曾雪强..融合情感分布的多标签emoji预测模型[J].山西大学学报（自然科学版）,2025,48(5):849-858,10.基金项目
国家自然科学基金(62266021) （62266021）
江西省教育厅科学技术研究(GJJ2200330) （GJJ2200330）
