面向教育大数据情感分类的多方面情感注意力模型

被引：4

作者：

翟冠霖 ^{[1
,2
]}

杨燕 ^{[1
,2
]}

汪衡 ^{[1
,2
]}

杜圣东 ^{[1
,2
]}

机构：

[1] 西南交通大学信息科学与技术学院

[2] 西南交通大学四川省云计算与智能技术高校重点实验室

来源：

模式识别与人工智能 | 2019年 / 32卷 / 09期

关键词：

情感分析; 教育大数据; 注意力机制; 神经网络;

D O I：

10.16451/j.cnki.issn1003-6059.201909007

中图分类号：

TP391.1 [文字信息处理]; TP311.13 []; TP183 [人工神经网络与计算];

学科分类号：

1201 ;

摘要：

针对高校课程评价方法效率较低、工作量较大等问题,文中提出多方面情感注意力模型(Multi-ASAM).使用神经网络将句子分别与句中的各个方面进行嵌入,加入情感资源注意力,在考虑方面间的关系对于情感极性影响的同时,考虑情感资源对于情感极性的贡献,从而取得更好的分类效果.实验表明,在教育领域和其它领域的应用中Multi-ASAM性能有部分提升.

引用

页码：828 / 834

页数：7

共 27 条

[1] Attention-based LSTM for Aspect-level Sentiment Classification. Wang Y,Huang M,Zhao L,et al. Conference on Empirical Methods in Natural Language Processing . 2016
[2] Hierarchical Attention Networks for Document Classification. Yang Zichao,Yang Diyi,Dyer Chris,et al. Proceedings of the 2016 Conference on North American Chapter of the Association for Computational Linguistics of Human Language Technologies (NAACL-HLT 2016) . 2016
[3] Attention-based LSTM Network for Cross-Lingual Sentiment Classification. Zhou X,Wan X,Xiao J. Conference on Empirical Methods in Natural Language Processing . 2016
[4] Sentiment analysis: Capturing favorability using natural language processing. NASUKAWA T,YI J. Proceedings of the 2nd International Conference on Knowledge Capture . 2003
[5] Which Contribution Does EDM Provide to Computer-Based Learning Environments. Bousbia,N,Belamri,I. Educational Data Mining . 2014
[6] Glove:Global Vectors for Word Representation. PENNINGTON J,SOCHER R,MANNING C D. Proc of the Conference on Empirical Methods in Natural Language Processing . 2014
[7] Translating Learning into Numbers: A Generic Framework for Learning Analytics[J] . &nbspJournal of Educational Technology & Society . 2012 (3)
[8] A Structured Self-attentive Sentence Embedding[C/OL]. LIN Z H,FENG M W,DOS SANTOS C N,et al. https://openreview.net/pdf?id=BJC_jUqxe . 2019
[9] Long short-term memory
Hochreiter, S
Schmidhuber, J
[J]. NEURAL COMPUTATION, 1997, 9 (08) : 1735 - 1780
[10] Lexicon Integrated CNN Models with Attention for Sentiment Analysis[C/OL]. SHIN B,LEE T,CHOI J D. https://arxiv.org/pdf/1610.06272.pdf . 2019

← 1 2 3 →