一种基于情感特征表示的跨语言文本情感分析模型  

A Cross-lingual Sentiment Analysis Model Based on Sentiment-aware Feature Representation

作　　者：徐月梅[1] 施灵雨 蔡连侨[1] XU Yuemei;SHI Lingyu;CAI Lianqiao(School of Information Science and Technology,Beijing Foreign Studies University,Beijing 100089,China)

机构地区：[1]北京外国语大学信息科学技术学院,北京100089

出　　处：《中文信息学报》2022年第2期129-141,共13页Journal of Chinese Information Processing

基　　金：中央高校基本科研业务费专项资金(2022JJ006)。

摘　　要：基于深度学习的跨语言情感分析模型需要借助预训练的双语词嵌入(Bilingual Word Embedding, BWE)词典获得源语言和目标语言的文本向量表示。为了解决BWE词典较难获得的问题,该文提出一种基于词向量情感特征表示的跨语言文本情感分析方法,引入源语言的情感监督信息以获得源语言情感感知的词向量表示,使得词向量的表示兼顾语义信息和情感特征信息,用于跨语言文本的情感预测。实验以英语为源语言,分别以汉语、法语、德语、日语、韩语和泰语6种语言为目标语言进行跨语言情感分析。实验结果表明,该文所提模型与机器翻译方法、不采用情感特征表示的跨语言情感分析方法比较,能够分别提高约9.3%和8.7%预测准确率。该模型在德语上的跨语言情感分析效果最好,英语与德语同属日耳曼语族,在语法和语义上更为接近,符合实验预期。实验部分对影响跨语言情感分析模型的相关因素进行了分析。In cross-lingual sentiment analysis, pre-trained Bilingual Word Embedding(BWE) dictionaries are leveraged to generate text vector representations of source and target languages. In order to obtain a qualified BWE dictionary, a novel model is proposed to utilize the affective features in source language as supervised information for word representation generation. The representations we pre-trained contain both semantic and emotional information, suitable for sentiment prediction in target language. In our cross-lingual sentiment analysis experiments, the source language is English, and the target languages include Chinese, French, German, Japanese, Korean and Thai. The results show that the accuracy of our proposed model is about 9.3% higher than Machine Translation(MT) based method, and 8.7% higher than parallel method without sentiment-aware representations. As expected, the experiments on English and German sentiment classification achieved best performance, for both languages belong to the Germanic language group and are more similar in grammar and semantics.

关 键 词：跨语言情感分析 情感感知 生成对抗网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]