基于CNN-BiLSTM-HAN混合神经网络的高校图书馆社交网络平台细粒度情感分析

doi:10.13998/j.cnki.issn1002-1248.21-0382

摘要/Abstract

摘要： [目的/意义]从高校图书馆社交网络平台用户评论数据挖掘角度出发,对用户评论情感极性进行细粒度分析,为高校图书馆了解用户真实情感倾向并提升服务质量提供科学依据。[方法/过程]以国内高校图书馆社交网络平台用户中文评论数据为研究对象,通过TensorFlow深度学习框架,利用Keras人工神经网络库,将卷积神经网络（Convolution Neural Network,CNN）和双向长短时记忆网络（Bidirectional Long Short Term Memory,BiLSTM）结合,并引入层次化注意力机制（Hierarchical Attention,HAN）,构建基于CNN-BiLSTM-HAN混合神经网络的情感分析模型。[结果/结论]利用真实高校图书馆社交网络平台用户评论数据集进行实验,本文方法取得93.38%的准确率,结果表明本文模型的有效性。模型较为复杂,导致模型训练时间上较长,方法模型的普适性有待进一步检验,表情符号信息没有得到有效利用,参数设置尚需进一步研究。

关键词: 高校图书馆, 社交网络平台, 卷积神经网络, 双向长短时记忆网络, 层次化注意力机制, 情感分析

Abstract: [Purpose/Significance] From the perspective of data mining of user comments on a social network platform of a university library, the sentiment polarity of user comments is analyzed in a fine-grained way. It provides scientific basis for a university library to understand the real sentiment tendency of its users and improve its service quality. [Method/Process] This paper takes the Chinese comments data of social network platform users of domestic university libraries as the research object. Through the TensorFlow deep learning framework, we used Keras artificial neural network library, combined convolution neural network and bidirectional long short term memory network, introduced hierarchical attention mechanism, and constructed sentiment analysis model based on CNN-BiLSTM-HAN hybrid neural network. [Results/Conclusions] The experiment is carried on by using the data set of user comments on the real social network platform of a university library. The accuracy of this method is 93.38%, and the results show that the model is effective. The model is more complex, as a result, the training time of the model is longer, the universality of the method model needs to be further tested., Emoticons are not used effectively, and the parameter setting needs further study.

Key words: university library, social network platform, convolution neural network, bidirectional long short term memory, hierarchical attention mechanism, sentiment analysis

中图分类号:

G203

李博, 李洪莲, 关青, 刘杨. 基于CNN-BiLSTM-HAN混合神经网络的高校图书馆社交网络平台细粒度情感分析[J]. 农业图书情报学报, 2022, 34(4): 63-73.

LI Bo, LI Honglian, GUAN Qing, LIU Yang. Fine-grained Sentiment Analysis of Social Network Platform of University Libraries Based on CNN-BiLSTM-HAN Hybrid Neural Network[J]. Journal of Library and Information Science in Agriculture, 2022, 34(4): 63-73.

参考文献

[1] 柳益君, 何胜, 吴智勤, 等. 基于用户社交网络分析的高校图书馆主题多样性阅读推荐[J]. 图书情报工作, 2018, 62(8): 67-73.
LIU Y J, HE S, WU Z Q, et al.Reading recommendation with subject diversity of university libraries based on analysis of user social network[J]. Library and information service, 2018, 62(8): 67-73.
[2] MARZ N, WARREN J.Big data: Principles and best practices of scalable real time data systems[M]. Manning publications co, 2015.
[3] 王晰巍, 贾若男, 王铎, 等. 图书情报领域人工智能的研究热点及发展趋势研究[J]. 图书情报工作, 2019, 63(1): 70-80.
WANG X W, JIA R N, WANG D, et al.Research on the development trend of artificial intelligence research in library and information field[J]. Library and information service, 2019, 63(1): 70-80.
[4] MOHEY D. A survey on sentiment analysis challenges[EB/OL]. [2016-04-26].http://www.sciencedirect.com/science/arti-cle/pii/S10
18363916300071.
[5] 唐晓波, 刘广超. 细粒度情感分析研究综述[J]. 图书情报工作, 2017, 61(5): 132-140.
TANG X B, LIU G C.Research review on fine-grained sentiment analysis[J]. Library and information service, 2017, 61(5): 132-140.
[6] PANG B, LEE L, VAITHYANTHAN S.Thumbs up: Sentiment clas-sification using machine learning techniques[C]. Proceedings of the conference on empirical methods in natural language processing, Stroudsburg, USA, 2002: 79-86.
[7] BARBOSA L, FENG J.Robust sentiment detection on twitter from biased and noisy data[C]. International conference on computational linguistics: Posters, association for computational linguistic, 2010: 36-44.
[8] 张文亮, 付枭男, 王彦芳. 我国省级公共图书馆评价研究——以大众点评网数据为例[J]. 图书情报工作, 2019, 63(5): 51-60.
ZAHNG W L, FU X N, WANG Y F.Research on evaluation of provincial public library - Taking dianping.com data as an example[J]. Library and information service, 2019, 63(5): 51-60.
[9] 毕达天, 王福. 移动图书馆场景化信息接受过程的情感变化研究[J]. 图书情报工作, 2019, 63(6): 20-28.
BI D T, WANG F.Emotional changes in scenario acceptance process of mobile library[J]. Library and information service, 2019, 63(6): 20-28.
[10] 曾子明, 杨倩雯. 基于LDA和AdaBoost多特征组合的微博情感分析[J]. 数据分析与知识发现, 2018, 2(8): 51-59.
ZENG Z M, YANG Q W.Sentiment analysis for micro-blogs with LDA and AdaBoost[J]. Data analysis and knowledge discovery, 2018, 2(8): 51-59.
[11] KALCHBRENNER N, GREFENSTETTE E, BLUNSOM P.A convolutional neural network for modelling sentences[J]. EprintArxiv, 2014, 1.
[12] KIM Y.Convolutional neural networks for sentence classification[J]. EprintArxiv, 2014.
[13] BENGIO Y, DUCHARME R, VINCENT P, et al.A neural probabilistic language model[J]. Journal of machine learning research, 2003, 3: 1137-1155.
[14] 周锦峰, 叶施仁, 王晖. 卷积神经网络在短文本情感多分类标注应用[J]. 计算机工程与应用, 2018, 54(22): 133-138, 149.
ZHOU J F, YE S R, WANG H.Application of convolutional neural network in multi-category classification for short text sentiment[J]. Computer engineering and applications, 2018, 54(22): 133-138, 149.
[15] HAI H D, PWC P, ANGELIKA M, et al.Deep learning for Aspect- Based sentiment analysis: A comparative review[J]. Expert systems with applications, 2019(118): 272-299.
[16] HUYTIEN N, MINH L N.An ensemble method with sentiment features and clustering support[J]. Neurocomputing, 2019(370): 155-165.
[17] HOON-KENG P, WUN-SHE Y, YEE-KAI T, et al.Hierarchical gated recurrent neural network with adversarial and virtual adversarial training on text classification[J]. Neural networks, 2019(119): 299-312.
[18] NIKHIL P, MANISH G, PONNURANGAM K, et al. A distant supervision based approach to medical persona classification[J]. Journal of biomedical informatics, 2019(94).
[19] SU C, LI J C, PENG Y, et al.Chinese metaphor sentiment computing via considering culture[J]. Neurocomputing, 2019(352): 33-41.
[20] HINTON G E.Learning distributed representations of concepts[C]. Eighth conference of the cognitive science society, 1989.
[21] WANG Y, HUANG M, ZHU X, et al.Attention-based LSTM for aspect-level sentiment classification[C]. Conference on empirical methods in natural language processing, 2017: 606-615.
[22] 余本功, 张培行, 许庆堂. 基于F-BiGRU情感分析的产品选择方法[J]. 数据分析与知识发现, 2018, 2(9): 22-30.
YU B G, ZHANG P H, XU Q T.Selecting products based on F-BiGRU sentiment analysis[J]. Data analysis and knowledge discovery, 2018, 2(9): 22-30.
[23] 胡荣磊, 芮璐, 齐筱, 等. 基于循环神经网络和注意力模型的文本情感分析[J]. 计算机应用研究, 2019, 36(11): 3282-3285.
HU R L, RUI L, QI X, et al.Text sentiment analysis based on recurrent neural networks and attention model[J]. Application research of computers, 2019, 36(11): 3282-3285.
[24] 郝志峰, 黄浩, 蔡瑞初, 等. 基于多特征融合与双向RNN的细粒度意见分析[J]. 计算机工程, 2018, 44(7): 199-204, 211.
HAO Z F, HUANG H, CAI R C, et al.Fine-grained opinion analysis based on multi-feature fusion and bidirectional RNN[J]. Computer engineering, 2018, 44(7): 199-204, 211.
[25] BAHDANAU D, CHO K, BENGIO Y.Neural machine translation by jointly learning to align and translate[J]. ArXiv preprint arxiv, 2014: 1409-1473.
[26] SCHUSTER M, PALIWAL K K.Bidirectional recurrent neural networks[J]. IEEE transactions on signal processing, 1997, 45(11): 2673-2681.
[27] MNIH V, HEESS N, GRAVES A, et al.Recurrent models of visual attention[C]. Advances in neural Information processing systems, 2014(27): 2204-2212.