| 50 | 0 | 43 |
| 下载次数 | 被引频次 | 阅读次数 |
针对网络用户的传统人格分类方法提取文本语义特征不充分、分类准确率低的问题，提出一种基于文本图表示学习的人格分类方法。该方法利用自然语言处理技术，并结合深度学习和图网络模型，设计一种自适应图卷积网络(adaptive graph convolutional network, ADGCN),通过自适应调整机制优化节点表示，平衡了节点特征的局部与全局信息。在Kaggle数据集上的测试实验表明，F1分数最高为80%,且平均F1分数达到71.14%,比传统机器学习方法和预训练模型BERT提高近20%,展现了模型计算效率上的优越性。
Abstract：To solve the problems of insufficient text semantic features and low classification accuracy of traditional personality classification methods for network users, a personality classification method based on text graph representation learning is proposed.This method uses natural language processing technology, combined with deep learning and graph network model, to build a new type of network user personality classification model, and designs an adaptive graph convolutional network(ADGCN).The node representation is optimized by an adaptive adjustment mechanism, which balances the local and global information of node features.Experiments on the Kaggle dataset show that the F1 score is up to 80%,and the average F1 score reaches 71.14%,which is nearly 20% higher than the traditional machine learning method and BERT pre-training model, showing the superiority of the model's computational efficiency.
[1] 景永霞，苟和平，刘强.基于BERT语义分析的短文本分类研究[J].兰州文理学院学报(自然科学版),2023,37(6):46-49.JING Y X,GOU H P,LIU Q.Classification study on online short text based on BERT semantic analysis[J].Journal of Lanzhou University of Arts and Science(Natural Sciences),2023,37(6):46-49.(in Chinese)
[2] 吕艳辉，刘明鑫.面向文本识别的CRNN模型的改进[J].沈阳理工大学学报，2024,43(4):27-31.Lü Y H,LIU M X.Improvement of CRNN model for text recognition[J].Journal of Shenyang Ligong University,2024,43(4):27-31.(in Chinese)
[3] 苏易礌，李卫军，刘雪洋，等.基于图神经网络的文本分类方法研究综述[J/OL].计算机工程与应用，2024:1-19(2024-06-20)[2024-06-30].https://kns.cnki.net/kcms/detail/11.2127.TP.20240620.1033.006.html.SU Y L,LI W J,LIU X Y,et al.A review of text classification methods based on graph neural networks[J/OL].Computer Engineering and Applications,2024:1-19(2024-06-20)[2024-06-30].https://kns.cnki.net/kcms/detail/11.2127.TP.20240620.1033.006.html.(in Chinese)
[4] 刘晓明，李丞正旭，吴少聪，等.文本分类算法及其应用场景研究综述[J/OL].计算机学报，2024:1-44(2024-02-29)[2024-06-30].https://kns.cnki.net/kcms/detail/11.1826.TP.20240229.1608.002.html.LIU X M,LI C Z X,WU S C,et al.A survey of text classification algorithms and application scenarios[J/OL].Chinese Journal of Computers,2024:1-44(2024-02-29)[2024-06-30].https://kns.cnki.net/kcms/detail/11.1826.TP.20240229.1608.002.html.(in Chinese)
[5] 廖春林，张宏军，廖湘琳，等.开源自然语言处理工具综述[J].计算机工程与应用，2023,59(22):36-56.LIAO C L,ZHANG H J,LIAO X L,et al.Survey of open source natural language processing tools[J].Computer Engineering and Applications,2023,59(22):36-56.(in Chinese)
[6] 闫滢钰，汶东震，张冬瑜，等.结合主题模型的中国古代诗人大五人格预测[J].山西大学学报(自然科学版),2023,46(3):546-556.YAN Y Y,WEN D Z,ZHANG D Y,et al.Combining topic model for ancient Chinese poets big five personality traits analysis[J].Journal of Shanxi University(Natural Science Edition),2023,46(3):546-556.(in Chinese)
[7] 王江晴，陈思敏，刘晶，等.基于上下文语义的社交网络用户人格预测[J].中南民族大学学报(自然科学版),2020,39(3):289-294.WANG J Q,CHEN S M,LIU J,et al.Social network user’s personality prediction based on context semantics[J].Journal of South-Central University for Nationalities(Natural Science Edition),2020,39(3):289-294.(in Chinese)
[8] UTAMI N A,MAHARANI W,ATASTINA I.Personality classification of facebook users according to big five personality using SVM(support vector machine)method[J].Procedia Computer Science,2021,179:177-184.
[9] KHAN A S,AHMAD H,ZUBAIR M,et al.Personality classification from online text using machine learning approach[J].International Journal of Advanced Computer Science and Applications,2020,11(3):460-476.
[10] CHOONG E J,VARATHAN K D.Predicting judging-perceiving of Myers-Briggs type indicator(MBTI)in online social forum[J].PeerJ,2021,9:e11382.
[11] PANDEY R,SINGH J P.BERT-LSTM model for sarcasm detection in code-mixed social media post[J].Journal of Intelligent Information Systems,2023,60(1):235-254.
[12] HOU J,LI X,ZHU R,et al.A neural relation extraction model for distant supervision in counter-terrorism scenario[J].IEEE Access,2020,8:225088-225096.
[13] HUANG Y,LI Z X,DENG W,et al.D-BERT:incorporating dependency-based attention into BERT for relation extraction[J].CAAI Transactions on Intelligence Technology,2021,6(4):417-425.
[14] 杨帅，王瑞琴，马辉.基于多通道的边学习图卷积网络[J].电信科学，2022,38(9):95-104.YANG S,WANG R Q,MA H.Multi-channel based edge-learning graph convolutional network[J].Telecommunications Science,2022,38(9):95-104.(in Chinese)
[15] 程旅航.图卷积神经网络的平滑性研究[D].长沙：中南大学，2022.
[16] FURNHAM A.The big five versus the big four:the relationship between the myers-briggs type indicator(MBTI)and NEO-PI five factor model of personality[J].Personality and Individual Differences,1996,21(2):303-307.
[17] LIN H.DLP-personality detection:a text-based personality detection framework with psycholinguistic features and pre-trained features[J].Multimedia Tools and Applications,2024,83(13):37275-37294.
基本信息:
DOI：
中图分类号:TP391.1;TP18
引用信息:
[1]刘猛,范摇珊,刘芳等.基于文本图表示学习的人格分类方法[J].沈阳理工大学学报,2025,44(04):7-12.
基金信息:
辽宁省教育厅高等学校基本科研重点项目(LJ212410144013); 沈阳市自然科学基金项目(22-315-6-10); 沈阳市中青年科技创新人才支持计划项目(RC210280)