基于多媒体信息的双向LSTM情感分析方法

doi:10.3969/j.issn.1006-2475.2019.02.015

摘要/Abstract

摘要： 随着信息技术的飞速发展，智慧政务的建设在中国如火如荼地展开。为了更好地服务社会，获取舆论的情感倾向变得至关重要。然而，由于媒体数据的多样性，例如讨论话题、文本正文、正文回复以及文本字数限制等原因，人们不仅要对文本正文进行分析，还必须对文本回复、讨论话题等多样文本信息，以及诸如表情符号、社交关系等因素进行建模。遗憾的是，很少有研究工作针对推文文本的回复及多媒体信息进行建模。本文针对推文正文回复、话题以及多媒体信息，提出一种新的双向长短时记忆网络CBi-LSTM (Content Bi-LSTM)对舆论进行情感分析。实验表明，文本信息和多媒体信息的融合能显著提高情感分析的准确性。

关键词: 多媒体信息, 情感分析, 双向长短记忆网络

Abstract: With the rapid development of information technology, the construction of intelligent government is in full swing in China. In order to serve society better, sentiment analysis is to be important in the future. However, due to the variety of the media data, such as the content of tweet, the title of topics, the reply and the limitation of the content, we not only need to analyze the content of tweets, but require to pay attention to some media information, such as reply and topics. While few work study media information to model context, this paper proposes a new model CBi-LSTM (Content Bi-LSTM) to study sentiment classification of multimedia information, such as reply, topic and so on. Experiments show that the fusion of text information and multimedia information can improve sentiment classification remarkably.

Key words: multimedia information, sentiment analysis, Bi-LSTM

中图分类号:

TP391

丁岩1,2，鲍焱1,2，胡晓1,2. 基于多媒体信息的双向LSTM情感分析方法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2019.02.015.

DING Yan1,2, BAO Yan1,2, HU Xiao1,2. Sentiment Analysis Based on Bi-LSTM with Multimedia Information[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2019.02.015.

参考文献

［1］ HU M Q, LIU B. Mining and summarizing customer reviews［C］// Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2004:168-177.
［2］ LIU B, ZHANG L. A survey of opinion mining and sentiment analysis［M］// Mining Text Data. Springer, 2012:415-463.
［3］ HU M Q, LIU B. Opinion extraction and summarization on the Web［C］// Proceedings of the 21st National Conference on Artificial Intelligence. 2006,2:1621-1624.
［4］谢丽星,周明,孙茂松. 基于层次结构的多策略中文微博情感分析和特征抽取［J］. 中文信息学报, 2012,26(1):73-83.
［5］ PANG B, LEE L, VAITHYANATHAN S. Thumbs up? Sentiment classification using machine learning techniques［C］// Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing. 2002:79-86.
［6］ FELDMAN R. Techniques and applications for sentiment analysis［J］. Communications of the ACM, 2013,56(4):82-89.
［7］ GHOSH S, VINYALS O, STROPE B, et al. Contextual LSTM (CLSTM) Models for Large Scale NLP Tasks［DB/OL］. (2016-05-31). https://arxiv.org/pdf/1602.06291.pdf.
［8］ HU X, TANG J L, GAO H J, et al. Unsupervised sentiment analysis with emotional signals［C］// Proceedings of the 22nd International Conference on World Wide Web. 2013:607-618.
［9］ KALCHBRENNER N, GREFENSTETTE E, BLUNSOM P. A convolutional neural network for modelling sentences［C］// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. 2014:655-665.
［10］KIM Y. Convolutional neural networks for sentence classification［C］// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014:1746-1751.
［11］DENG H B, HAN J W, LI H, et al. Exploring and inferring user-user pseudo-friendship for sentiment analysis with heterogeneous networks［J］. Statistical Analysis and Data Mining, 2014,7(4):308-321.
［12］TAN C H, LEE L, TANG J, et al. User-level sentiment analysis incorporating social networks［C］// Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2011:1397-1405.
［13］WANG X, LIU Y C, SUN C J, et al. Predicting polarities of Tweets by composing word embeddings with long short-term memory［C］// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015:1343-1353.
［14］TAI K S, SOCHER R, MANNING C D. Improved semantic representations from tree-structured long short-term memory networks［C］// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015:1556-1566.
［15］DONG L, WEI F R, TAN C Q, et al. Adaptive recursive neural network for target-dependent Twitter sentiment classification［C］// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. 2014,2:49-54.
［16］HU X, TANG L, TANG J L, et al. Exploiting social relations for sentiment analysis in Microblogging［C］// Proceedings of the 6th ACM International Conference on Web Search and Data Mining. 2013:537-546.
［17］IRSOY O, CARDIE C. Deep recursive neural networks for compositionality in language［C］// Proceedings of the 27th International Conference on Neural Information Processing Systems. 2014,2:2096-2104.
［18］MOHAMMAD S M, KIRITCHENKO S, ZHU X D. NRC-Canada: Building the state-of-the-art in sentiment analysis of Tweets［C］// Proceedings of the 2nd Joint Conference on Lexical and Computational Semantics and the 7th International Workshop on Semantic Evaluation. 2013,2:321-327.
［19］MUKHERJEE S, BHATTACHARYYA P. Sentiment analysis in Twitter with lightweight discourse analysis［C］// Proceedings of the 24th International Conference on Computational Linguistics. 2012:1847-1864.
［20］IRSOY O, CARDIE C. Opinion mining with deep recurrent neural networks［C］// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014:720-728.
［21］REN Y F, ZHANG Y, ZHANG M S, et al. Context-sensitive Twitter sentiment classification using neural network［C］// Proceedings of the 30th AAAI Conference on Artificial Intelligence. 2016:215-221.
［22］SEVERYN A, MOSCHITTI A. Twitter sentiment analysis with deep convolutional neural networks［C］// Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2015:959-962.
［23］TANG D Y, QIN B, LIU T. Document modeling with gated recurrent neural network for sentiment classification［C］// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015:1422-1432.
［24］VANZO A, CROCE D, BASILI R. A context-based model for sentiment analysis in Twitter［C］// Proceedings of the 25th International Conference on Computational Linguistics. 2014:2345-2354.
［25］YANG B S, CARDIE C. Context-aware learning for sentence-level sentiment analysis with posterior regularization［C］// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. 2014:325-335.
［26］ZHANG X X, LAPATA M. Chinese poetry generation with recurrent neural networks［C］// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014:670-680.
［27］HUANG M L, CAO Y J, DONG C. Modeling Rich Contexts for Sentiment Classification with LSTM［DB/OL］. (2016-05-05). https://arxiv.org/pdf/1605.01478.pdf.
［28］BENGIO Y, SIMARD P, FRASCONI P. Learning long-term dependencies with gradient descent is difficult［J］. IEEE Transactions on Neural Networks, 1994,5(2):157-166.
［29］Zeiler M D. ADADELTA: An Adaptive Learning Rate Method［DB/OL］. (2012-12-22). https://arxiv.org/pdf/1212.5701.pdf.

[1]	李诗月, 孟佳娜, 于玉海, 李雪莹, 许英傲. 基于知识增强的方面级情感分析方法[J]. 计算机与现代化, 2023, 0(10): 1-8.
[2]	姚春华, 张学磊, 宋馨宇, 张举, 蔡佳志, 冯翱. 一种基于图卷积神经网络和依存分析的财经新闻情感分析方法[J]. 计算机与现代化, 2022, 0(05): 33-39.
[3]	冯茹嘉, 张海军, 潘伟民. 基于情感分析和Transformer模型的微博谣言检测[J]. 计算机与现代化, 2021, 0(10): 1-7.
[4]	尼格拉木·买斯木江, 艾孜尔古丽·玉素甫. 基于BERT及双向GRU模型的慕课用户评论情感倾向性分析[J]. 计算机与现代化, 2021, 0(04): 20-26.
[5]	徐龙. 基于自注意力和胶囊网络的短文本情感分析[J]. 计算机与现代化, 2020, 0(07): 61-64.
[6]	沈然，林恺丰，吴慧. 一种用于供电服务评估的多模态多任务框架[J]. 计算机与现代化, 2018, 0(12): 51-.
[7]	李继东，王移芝. 基于扩展词典与语义规则的中文微博情感分析[J]. 计算机与现代化, 2018, 0(02): 89-.
[8]	王娜娜，李向前. 文本情感倾向性分析[J]. 计算机与现代化, 2017, 0(7): 10-15+52.
[9]	伊尔夏提·吐尔贡,吾守尔·斯拉木,热西旦木·吐尔洪太,于清. 维吾尔文情感语料库的构建与分析[J]. 计算机与现代化, 2017, 0(4): 67-72.
[10]	石强强1，赵应丁2,3，杨红云2,3. 基于SVM的酒店客户评论情感分析[J]. 计算机与现代化, 2017, 0(3): 117-.
[11]	张建华,梁正友. 基于情感词抽取与LDA特征表示的情感分析方法[J]. 计算机与现代化, 2014, 0(5): 79-83.