Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (4): 1056-1061.DOI: 10.11772/j.issn.1001-9081.2022030469
• Artificial intelligence • Previous Articles
Cheng FANG1(), Bei LI2, Ping HAN1, Qiong WU3
Received:
2022-04-13
Revised:
2022-09-27
Accepted:
2022-09-28
Online:
2023-04-11
Published:
2023-04-10
Contact:
Cheng FANG
About author:
LI Bei, born in 1993, M. S. candidate. Her research interests include natural language processing.Supported by:
通讯作者:
方澄
作者简介:
李贝(1993—),女,四川绵阳人,硕士研究生,主要研究方向:自然语言处理;基金资助:
CLC Number:
Cheng FANG, Bei LI, Ping HAN, Qiong WU. Fine-grained emotion classification of Chinese microblog based on syntactic dependency graph[J]. Journal of Computer Applications, 2023, 43(4): 1056-1061.
方澄, 李贝, 韩萍, 吴琼. 基于语法依存图的中文微博细粒度情感分类[J]. 《计算机应用》唯一官方网站, 2023, 43(4): 1056-1061.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.joca.cn/EN/10.11772/j.issn.1001-9081.2022030469
情感 | 通用微博 | 疫情微博 |
---|---|---|
开心 | 清晨醒来,发现外面下着雨感觉好有诗意 | 感谢有你@#致敬疫情前线医护人员# |
伤心 | 跌跌撞撞磕磕碰碰这儿疼哪儿酸浑身是伤,崩溃想哭 | [泪][泪][泪]这几天看的新闻都感觉是一部电视剧 |
惊讶 | 关灯后,我竟然听到了蚊子的哼哼声,是我幻听了吗 | #新型肺炎最长潜伏期约14天#还有两天才出潜伏期[泪]?? |
害怕 | 事后还是有点心有余悸,安全第一吧! | 完全感觉不到明天就是除夕了全国都处在一种恐慌的状态里 |
生气 | 嘴巴挑的不得了,以后不给你吃了 | 歪日[衰] |
无情绪 | 言归正传,先来看看魔神王的背景 | 普通人能做的:尽量远离人群,外出戴口罩,向家里人科普宣传防护知识 |
Tab. 1 Data samples
情感 | 通用微博 | 疫情微博 |
---|---|---|
开心 | 清晨醒来,发现外面下着雨感觉好有诗意 | 感谢有你@#致敬疫情前线医护人员# |
伤心 | 跌跌撞撞磕磕碰碰这儿疼哪儿酸浑身是伤,崩溃想哭 | [泪][泪][泪]这几天看的新闻都感觉是一部电视剧 |
惊讶 | 关灯后,我竟然听到了蚊子的哼哼声,是我幻听了吗 | #新型肺炎最长潜伏期约14天#还有两天才出潜伏期[泪]?? |
害怕 | 事后还是有点心有余悸,安全第一吧! | 完全感觉不到明天就是除夕了全国都处在一种恐慌的状态里 |
生气 | 嘴巴挑的不得了,以后不给你吃了 | 歪日[衰] |
无情绪 | 言归正传,先来看看魔神王的背景 | 普通人能做的:尽量远离人群,外出戴口罩,向家里人科普宣传防护知识 |
数据集 | 训练集 | 数据增强 | 验证集 | 测试集 |
---|---|---|---|---|
通用微博 | 27 768 | 30 512 | 2 000 | 5 000 |
疫情微博 | 8 606 | 12 419 | 2 000 | 3 000 |
Tab. 2 Data scale
数据集 | 训练集 | 数据增强 | 验证集 | 测试集 |
---|---|---|---|---|
通用微博 | 27 768 | 30 512 | 2 000 | 5 000 |
疫情微博 | 8 606 | 12 419 | 2 000 | 3 000 |
参数 | 值 | 参数 | 值 |
---|---|---|---|
迭代轮数(Epoch) | 64 | Dropout_rate | 0.5 |
优化器(Optimizer) | Adam | 权重初始化 | 随机初始化 |
初始学习率 (Learning_rate) | 0.001 | 隐藏层单元数 (Hidden_unit) | 200 |
Batch_size | 16 |
Tab. 3 Parameter setting of model
参数 | 值 | 参数 | 值 |
---|---|---|---|
迭代轮数(Epoch) | 64 | Dropout_rate | 0.5 |
优化器(Optimizer) | Adam | 权重初始化 | 随机初始化 |
初始学习率 (Learning_rate) | 0.001 | 隐藏层单元数 (Hidden_unit) | 200 |
Batch_size | 16 |
模型 | F1值 | Macro_Ffinal | |
---|---|---|---|
通用 | 疫情 | ||
Text-CNN[ | 63.21 | 60.11 | 61.66 |
DPCNN[ | 65.64 | 63.43 | 64.54 |
FastText[ | 64.45 | 60.80 | 62.63 |
LSTM[ | 65.53 | 67.70 | 66.62 |
BiLSTM[ | 66.25 | 70.14 | 68.20 |
Text-Level-GNN[ | 68.10 | 69.43 | 68.77 |
BGCN[ | 69.65 | 72.21 | 69.89 |
SGCN | 71.50 | 73.77 | 72.64 |
Tab. 4 Comparison of classification results of different models
模型 | F1值 | Macro_Ffinal | |
---|---|---|---|
通用 | 疫情 | ||
Text-CNN[ | 63.21 | 60.11 | 61.66 |
DPCNN[ | 65.64 | 63.43 | 64.54 |
FastText[ | 64.45 | 60.80 | 62.63 |
LSTM[ | 65.53 | 67.70 | 66.62 |
BiLSTM[ | 66.25 | 70.14 | 68.20 |
Text-Level-GNN[ | 68.10 | 69.43 | 68.77 |
BGCN[ | 69.65 | 72.21 | 69.89 |
SGCN | 71.50 | 73.77 | 72.64 |
模型 | F1值 | |
---|---|---|
通用 | 疫情 | |
图卷积 | 63.84 | 65.21 |
图卷积+词向量特征 | 69.00 | 70.86 |
图卷积+词向量+表情特征 | 70.59 | 72.24 |
图卷积+词向量+表情特征+PMI特征 | 71.50 | 73.77 |
Tab.5 Feature ablation experiment results
模型 | F1值 | |
---|---|---|
通用 | 疫情 | |
图卷积 | 63.84 | 65.21 |
图卷积+词向量特征 | 69.00 | 70.86 |
图卷积+词向量+表情特征 | 70.59 | 72.24 |
图卷积+词向量+表情特征+PMI特征 | 71.50 | 73.77 |
情绪 | Precision | Recall | F1值 | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
通用 | 疫情 | 通用 | 疫情 | 通用 | 疫情 | |||||||
融合前 | 融合后 | 融合前 | 融合后 | 融合前 | 融合后 | 融合前 | 融合后 | 融合前 | 融合后 | 融合前 | 融合后 | |
开心 | 66.97 | 72.23 | 86.28 | 86.57 | 66.11 | 67.19 | 86.56 | 88.77 | 66.53 | 69.62 | 86.42 | 87.66 |
伤心 | 54.76 | 57.74 | 37.37 | 56.34 | 55.56 | 61.33 | 50.68 | 54.79 | 55.16 | 59.48 | 43.02 | 55.56 |
惊讶 | 59.36 | 54.42 | 11.01 | 15.43 | 34.85 | 51.21 | 17.65 | 36.76 | 43.92 | 52.76 | 13.56 | 21.74 |
害怕 | 57.50 | 58.33 | 37.76 | 52.35 | 65.71 | 76.67 | 28.42 | 46.84 | 61.33 | 66.26 | 32.43 | 49.44 |
生气 | 71.16 | 77.29 | 61.92 | 69.82 | 79.79 | 76.67 | 63.93 | 68.47 | 75.23 | 76.98 | 62.91 | 69.14 |
无情绪 | 81.63 | 81.91 | 57.73 | 58.13 | 76.77 | 80.51 | 59.62 | 64.62 | 79.13 | 81.20 | 58.66 | 61.20 |
Tab. 6 Emotion classification results comparison of models before and after fusing emoticon features
情绪 | Precision | Recall | F1值 | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
通用 | 疫情 | 通用 | 疫情 | 通用 | 疫情 | |||||||
融合前 | 融合后 | 融合前 | 融合后 | 融合前 | 融合后 | 融合前 | 融合后 | 融合前 | 融合后 | 融合前 | 融合后 | |
开心 | 66.97 | 72.23 | 86.28 | 86.57 | 66.11 | 67.19 | 86.56 | 88.77 | 66.53 | 69.62 | 86.42 | 87.66 |
伤心 | 54.76 | 57.74 | 37.37 | 56.34 | 55.56 | 61.33 | 50.68 | 54.79 | 55.16 | 59.48 | 43.02 | 55.56 |
惊讶 | 59.36 | 54.42 | 11.01 | 15.43 | 34.85 | 51.21 | 17.65 | 36.76 | 43.92 | 52.76 | 13.56 | 21.74 |
害怕 | 57.50 | 58.33 | 37.76 | 52.35 | 65.71 | 76.67 | 28.42 | 46.84 | 61.33 | 66.26 | 32.43 | 49.44 |
生气 | 71.16 | 77.29 | 61.92 | 69.82 | 79.79 | 76.67 | 63.93 | 68.47 | 75.23 | 76.98 | 62.91 | 69.14 |
无情绪 | 81.63 | 81.91 | 57.73 | 58.13 | 76.77 | 80.51 | 59.62 | 64.62 | 79.13 | 81.20 | 58.66 | 61.20 |
1 | SOCHER R, PENNINGTON J, HUANG E H, et al. Semi-supervised recursive autoencoders for predicting sentiment distributions[C]// Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2011: 151-161. |
2 | KIM Y. Convolutional neural networks for sentence classification[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2014:1746-1751. 10.3115/v1/d14-1181 |
3 | TAI K S, SOCHER R, MANNING C D. Improved semantic local 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 (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2015: 1556-1566. 10.3115/v1/p15-1150 |
4 | 万岩,杜振中. 融合情感词典和语义规则的微博评论细粒度情感分析[J]. 情报探索, 2020(11):34-41. 10.3969/j.issn.1005-8095.2020.11.005 |
WAN Y, DU Z Z. Fine-grained sentiment analysis of microblog comments based on fusion of sentiment lexicon and semantic rules[J]. Information Research, 2020(11):34-41. 10.3969/j.issn.1005-8095.2020.11.005 | |
5 | KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. (2017-02-22) [2022-02-20].. 10.48550/arXiv.1609.02907 |
6 | YAO L, MAO C S, LUO Y. Graph convolutional networks for text classification[C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2019:7370-7377. 10.1609/aaai.v33i01.33017370 |
7 | LAI Y N, ZHANG L F, HAN D H, et al. Fine-grained emotion classification of Chinese microblogs based on graph convolution networks[J]. World Wide Web, 2020, 23(5):2771-2787. 10.1007/s11280-020-00803-0 |
8 | 王光,李鸿宇,邱云飞,等. 基于图卷积记忆网络的方面级情感分类[J]. 中文信息学报, 2021, 35(8):98-106. 10.3969/j.issn.1003-0077.2021.08.013 |
WANG G, LI H Y, QIU Y F, et al. Aspect-based sentiment classification via memory graph convolutional network[J]. Journal of Chinese Information Processing, 2021, 35(8):98-106. 10.3969/j.issn.1003-0077.2021.08.013 | |
9 | 张军莲,张一帆,汪鸣泉,等. 基于图卷积神经网络的中文实体关系联合抽取[J]. 计算机工程, 2021, 47(12):103-111. |
ZHANG J L, ZHANG Y F, WANG M Q, et al. Joint extraction of Chinese entity relations based on graph convolutional neural network[J]. Computer Engineering, 2021, 47(12):103-111. | |
10 | ZHAO J, LIU K, XU L H. Book review: sentiment analysis: mining opinions, sentiments, and emotions[J]. Computational Linguistics, 2016, 42(3):595-598. 10.1162/coli_r_00259 |
11 | YANG Z L, DAI Z H, YANG Y M, et al. XLNet: generalized autoregressive pretraining for language understanding[C/OL]// Proceedings of the 33rd Conference on Neural Information Processing Systems [2022-02-14].. |
12 | DAI Z H, YANG Z L, YANG Y M, et al. Transformer-XL: attentive language models beyond a fixed-length context[C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2019:2978-2988. 10.18653/v1/p19-1285 |
13 | LI X W, NING H Y. Deep pyramid convolutional neural network integrated with self-attention mechanism and highway network for text classification[J]. Journal of Physics: Conference Series, 2020, 1642: No.012008. 10.1088/1742-6596/1642/1/012008 |
14 | JOULIN A, GRAVE E, BOJANOWSKI P, et al. Bag of tricks for efficient text classification[C]// Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2, Short Papers). Stroudsburg, PA: ACL, 2017:427-431. 10.18653/v1/e17-2068 |
15 | ZHOU P, SHI W, TIAN J, et al. Attention-based bidirectional long short-term memory networks for relation classification[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Stroudsburg, PA: ACL, 2016: 207-212. 10.18653/v1/p16-2034 |
16 | HUANG L Z, MA D H, LI S J, et al. Text level graph neural network for text classification[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg, PA: ACL, 2019:3444-3450. 10.18653/v1/d19-1345 |
17 | 方澄, 李贝, 韩萍. 基于全局特征图的半监督微博文本情感分类[J]. 信号处理, 2021, 37(6):1066-1074. 10.16798/j.issn.1003-0530.2021.06.018 |
FANG C, LI B, HAN P. Semi-supervised microblog text sentiment classification based on global feature graph[J]. Journal of Signal Processing, 2021, 37(6):1066-1074. 10.16798/j.issn.1003-0530.2021.06.018 |
[1] | Xu ZHANG, Long SHENG, Haifang ZHANG, Feng TIAN, Wei WANG. Pre-hospital emergency text classification model based on label confusion [J]. Journal of Computer Applications, 2023, 43(4): 1050-1055. |
[2] | Zhoubo XU, Puqing CHEN, Huadong LIU, Xin YANG. Deep graph matching model based on self-attention network [J]. Journal of Computer Applications, 2023, 43(4): 1005-1012. |
[3] | Rongjun CHEN, Xuanhui YAN, Chaocheng YANG. Fusion imaging-based recurrent capsule classification network for time series [J]. Journal of Computer Applications, 2023, 43(3): 692-699. |
[4] | Jiangfeng ZHANG, Tao YAN, Bin CHEN, Yuhua QIAN, Yantao SONG. Multi-depth-of-field 3D shape reconstruction with global spatio-temporal feature coupling [J]. Journal of Computer Applications, 2023, 43(3): 894-902. |
[5] | Yingmao YAO, Xiaoyan JIANG. Video-based person re-identification method based on graph convolution network and self-attention graph pooling [J]. Journal of Computer Applications, 2023, 43(3): 728-735. |
[6] | Xuedong HE, Shibin XUAN, Kuan WANG, Mengnan CHEN. DeepLabV3+ image segmentation algorithm fusing cumulative distribution function and channel attention mechanism [J]. Journal of Computer Applications, 2023, 43(3): 936-942. |
[7] | Tao PENG, Yalong KANG, Feng YU, Zili ZHANG, Junping LIU, Xinrong HU, Ruhan HE, Li LI. Pedestrian trajectory prediction based on multi-head soft attention graph convolutional network [J]. Journal of Computer Applications, 2023, 43(3): 736-743. |
[8] | Boyi FU, Yuncong PENG, Xin LAN, Xiaolin QIN. Survey of label noise learning algorithms based on deep learning [J]. Journal of Computer Applications, 2023, 43(3): 674-684. |
[9] | Ruoying WANG, Fan LYU, Liuqing ZHAO, Fuyuan HU. Floorplan generation algorithm integrating user requirements and boundary constraints [J]. Journal of Computer Applications, 2023, 43(2): 575-582. |
[10] | Yating SU, Cuixiang LIU. Three-dimensional human reconstruction model based on high-resolution net and graph convolutional network [J]. Journal of Computer Applications, 2023, 43(2): 583-588. |
[11] | Qi WANG, Hang LEI, Xupeng WANG. Deep face verification under pose interference [J]. Journal of Computer Applications, 2023, 43(2): 595-600. |
[12] | Ping WANG, Nan CHEN, Lei LU. Fall detection algorithm based on scene prior and attention guidance [J]. Journal of Computer Applications, 2023, 43(2): 529-535. |
[13] | Li’an ZHU, Hong ZHANG. Nonhomogeneous image dehazing based on dual-branch conditional generative adversarial network [J]. Journal of Computer Applications, 2023, 43(2): 567-574. |
[14] | Yangping LIN, Jia LIU, Pei CHEN, Mingshu ZHANG, Xiaoyuan YANG. Semi-generative video steganography scheme based on deep convolutional generative adversarial net [J]. Journal of Computer Applications, 2023, 43(1): 169-175. |
[15] | Jun ZHANG, Pengli WU, Lukui SHI, Jin SHI, Bin PAN. Deep learning model for multi-station temperature prediction combined with MOD11A1 and surface meteorological station data [J]. Journal of Computer Applications, 2023, 43(1): 321-328. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||