首先,经过Glove词嵌入和双向长短时记忆网络获取评论数据中文本词语的向量表示.然后,基于词语的句法信息、语义信息和上下文信息,构建异质融合图,并结合图注意力机制,学习评论中的文本特征,进而通过多层感知机融合基于自编码方法获取的表情符号特征,并输出关于虚假信息评论内容的情感极性向量.实验结果表明,与所有的基线模型相比,使用本文所提出的多模态情感分析模型能够充分挖掘社交网络用户表达观点和感情时表情符号与文本之间的潜在交互性,从而更为有效地评估虚假信息评论内容的情感倾向性,表征网络用户的情感态度或属性,进而为提出面向情感分析结果的社交网络虚假传播抑制策略提供用户情感分类方面的理论支撑.
In this paper, firstly,the vector representations of text words in comment data are obtained by using Glove word embedding and bidirectional long short-term memory networks. Then, the syntactic information, semantic information, and contextual information of the words are used to construct a heterogeneous fusion graph and combined with graph attention mechanism to learn the text features in the comments. Furthermore, the expression symbol features obtained on the basis of the auto-encoder method are fused through a multi-layer perceptron, and an emotional polarity vector about the disinformation comment content is output. The research results indicate that compared with all baseline models, the multimodal sentiment analysis model proposed in this paper can fully explore the potential interaction between emoticon and text when social network users express their opinions and emotions. This can more effectively evaluate the emotional tendency of disinformation comments, characterize the emotional attitudes or attributes of network users, and achieve effective classification of user emotions. Furthermore, the proposed model provides theoretical support for proposing strategies to suppress false propagation in social networks based on sentiment analysis results, in terms of user sentiment classification.
[1] MIRHOSEINI M, EARLY S, ELSHAMY N, et al. Actively open-minded thinking is key to combating fake news: a multimethod study[J]. Inf Manag, 2023, 60(3): 103761.DOI:10.1016/j.im.2023.103761.
[2] 徐健,张婧,宋玲钰,等.基于RoBERTa-BiLSTM-CRF融合模型的在线评论细粒度情感分析[J].系统工程理论与实践, 2023, 43(12): 3519-3536.DOI: 10.12011/SETP2022-2001.
[3] 栾碧雅.社交网络虚假信息传播影响因素及治理策略研究[D].长春:吉林大学, 2020.DOI:10.27162/d.cnki.gjlin.2020.001597.
[4] 翟羽佳,过南杉,阎嘉琪.突发公共卫生事件中虚假信息的时滞性扩散与情感关联分析[J].情报科学, 2021, 39(5): 62-69.DOI: 10.13833/j.issn.1007-7634.2021.05.009.
[5] LOU Y X, ZHANG Y, LI F, et al. Emoji-based sentiment analysis using attention networks[J]. ACM Trans Asian Low-Resour Lang Inf Process, 2020, 19(5): 1-13.DOI: 10.1016/j.chb.2021.106722.
[6] HAAK F. Design and development of an emoji sentiment lexicon[C] // Proceedings of the 16th International Symposium of Information Science(ISI 2021), Glückstadt: Verlag Werner Hülsbusch, 2021:432-438.DOI: 10.5283/epub.44960.
[7] 徐海杰.基于深度学习的情感分析研究[D].大庆:东北石油大学,2023.DOI: 10.26995/d.cnki.gdqsc.2022.000496.
[8] CHEN J, YAO Z Q, ZHAO S, et al. Fusion pre-trained emoji feature enhancement for sentiment analysis[J]. ACM Trans Asian Low-Resour Lang Inf Process, 2023, 22(4): 1-14.DOI: 10.1145/3578582.
[9] RODRÍGUEZ-IBÁNEZ M, CASÁNEZ-VENTURA A, CASTEJÓN-MATEOS F, et al. A review on sentiment analysis from social media platforms[J]. Expert Syst Appl, 2023, 223: 119862.DOI: 10.1016/j.eswa.2023.119862.
[10] 柴变芳,杨蕾,王建岭,等.集成局部和全局关键特征的文本情感分类方法[J]. 河北大学学报(自然科学版), 2021,41(2): 201-211.DOI: 10.3969/j.issn.1000-1565.2021.02.014.
[11] 李涛,薛刚,霍自祥,等.基于卷积神经网络的石英纤维复合材料损伤缺陷太赫兹智能识别[J].河北大学学报(自然科学版), 2022, 42(6):665-672.DOI: 10.3969/j.issn.1000-1565.2022.06.015.
[12] 张昱,苏仡琳,李继涛,等.基于增强多通道图注意力的推荐模型[J].河北大学学报(自然科学版), 2024, 44(2):190-198.DOI: 10.3969/j.issn.1000-1565.2024.02.010.
[13] JACOB Y, WINETRAUB Y, RAZ G, et al. Dependency network analysis(DEPNA)reveals context related influence of brain network nodes[J]. Sci Rep, 2016, 6: 27444.DOI: 10.1038/srep27444.
[14] 陈明红.信息生态系统中资源配置的博弈行为分析[J].情报理论与实践, 2010, 33(9): 17-22.DOI: 10.16353/j.cnki.1000-7490.2010.09.006.
[15] MA Y K, PENG H Y, CAMBRIA E. Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM[J].Proc AAAI Conf Artif Intell,2018, 32(1): 5876-5883.DOI: 10.1609/aaai.v32i1.12048.
[16] PHAN H T, NGUYEN N T, TRAN V C, et al. An approach for a decision-making support system based on measuring the user satisfaction level on Twitter[J]. Inf Sci, 2021, 561: 243-273.DOI: 10.1016/j.ins.2021.01.008.
[17] YAO L, MAO C S, LUO Y. Graph convolutional networks for text classification[J].Proc AAAI Conf Artif Intell, 2019, 33(1): 7370-7377.DOI: 10.1609/aaai.v33i01.33017370.
[18] CAMBRIA E, PORIA S, HAZARIKA D, et al. SenticNet 5: discovering conceptual primitives for sentiment analysis by means of context embeddings[J].Proc AAAI Conf Artif Intell,2018, 32(1): 1795-1802.DOI: 10.1609/aaai.v32i1.11559.
[19] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C] // Proceedings of the 5th International Conference on Learning Representations, Toulon: Association for Learning Representations, 2017: 1-14.DOI: 10.48550/arXiv.1609.02907. (
