PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection

Personality detection identifies personality traits in text. Current approaches often rely on deep learning networks for text representation but they overlook the significance of psychological language knowledge in connecting user language expression to psychological characteristics. Consequently, t...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenjuan Liu, Zhengyan Sun, Subo Wei, Shunxiang Zhang, Guangli Zhu, Lei Chen
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Connection Science
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/09540091.2023.2295820
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850230009593069568
author Wenjuan Liu
Zhengyan Sun
Subo Wei
Shunxiang Zhang
Guangli Zhu
Lei Chen
author_facet Wenjuan Liu
Zhengyan Sun
Subo Wei
Shunxiang Zhang
Guangli Zhu
Lei Chen
author_sort Wenjuan Liu
collection DOAJ
description Personality detection identifies personality traits in text. Current approaches often rely on deep learning networks for text representation but they overlook the significance of psychological language knowledge in connecting user language expression to psychological characteristics. Consequently, the accuracy of personality detection is compromised. To address this issue, this paper presents PS-GCN, a model integrating Psychological knowledge and Sentiment semantic features through Graph Convolution Networks. Firstly, the Bi-LSTM network captures local features of preprocessed sentences to accurately represent the output of sentence sentiment features. Secondly,  GCNs map psycholinguistic knowledge, forming semantic networks of entities and relationships. P-GCN is designed to capture the dependency information between psycholinguistic features, while S-GCN utilises syntactic structure analysis to gather more abundant information features and enhance semantic understanding ability. Finally, attention calculation is employed to reinforce key features and weaken irrelevant information. Additionally, a sentence group model captures combined features of related sentences, effectively utilising the text structure to mine sentimental features. Experimental results on multiple datasets demonstrate that the proposed method significantly improves the classification accuracy in personality detection tasks.
format Article
id doaj-art-2a4db33bb2a64d14ba4b67843faebd15
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-2a4db33bb2a64d14ba4b67843faebd152025-08-20T02:04:00ZengTaylor & Francis GroupConnection Science0954-00911360-04942024-12-0136110.1080/09540091.2023.2295820PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detectionWenjuan Liu0Zhengyan Sun1Subo Wei2Shunxiang Zhang3Guangli Zhu4Lei Chen5School of Computer Science and Engineering, Anhui University of Science & Technology, Huainan, People’s Republic of ChinaSchool of Computer Science, Huainan normal University, Huainan, People’s Republic of ChinaSchool of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of ChinaSchool of Computer Science and Engineering, Anhui University of Science & Technology, Huainan, People’s Republic of ChinaSchool of Computer Science and Engineering, Anhui University of Science & Technology, Huainan, People’s Republic of ChinaSchool of Computer Science, Huainan normal University, Huainan, People’s Republic of ChinaPersonality detection identifies personality traits in text. Current approaches often rely on deep learning networks for text representation but they overlook the significance of psychological language knowledge in connecting user language expression to psychological characteristics. Consequently, the accuracy of personality detection is compromised. To address this issue, this paper presents PS-GCN, a model integrating Psychological knowledge and Sentiment semantic features through Graph Convolution Networks. Firstly, the Bi-LSTM network captures local features of preprocessed sentences to accurately represent the output of sentence sentiment features. Secondly,  GCNs map psycholinguistic knowledge, forming semantic networks of entities and relationships. P-GCN is designed to capture the dependency information between psycholinguistic features, while S-GCN utilises syntactic structure analysis to gather more abundant information features and enhance semantic understanding ability. Finally, attention calculation is employed to reinforce key features and weaken irrelevant information. Additionally, a sentence group model captures combined features of related sentences, effectively utilising the text structure to mine sentimental features. Experimental results on multiple datasets demonstrate that the proposed method significantly improves the classification accuracy in personality detection tasks.https://www.tandfonline.com/doi/10.1080/09540091.2023.2295820Personality detectionBi-LSTMGCNattention
spellingShingle Wenjuan Liu
Zhengyan Sun
Subo Wei
Shunxiang Zhang
Guangli Zhu
Lei Chen
PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection
Connection Science
Personality detection
Bi-LSTM
GCN
attention
title PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection
title_full PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection
title_fullStr PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection
title_full_unstemmed PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection
title_short PS-GCN: psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection
title_sort ps gcn psycholinguistic graph and sentiment semantic fused graph convolutional networks for personality detection
topic Personality detection
Bi-LSTM
GCN
attention
url https://www.tandfonline.com/doi/10.1080/09540091.2023.2295820
work_keys_str_mv AT wenjuanliu psgcnpsycholinguisticgraphandsentimentsemanticfusedgraphconvolutionalnetworksforpersonalitydetection
AT zhengyansun psgcnpsycholinguisticgraphandsentimentsemanticfusedgraphconvolutionalnetworksforpersonalitydetection
AT subowei psgcnpsycholinguisticgraphandsentimentsemanticfusedgraphconvolutionalnetworksforpersonalitydetection
AT shunxiangzhang psgcnpsycholinguisticgraphandsentimentsemanticfusedgraphconvolutionalnetworksforpersonalitydetection
AT guanglizhu psgcnpsycholinguisticgraphandsentimentsemanticfusedgraphconvolutionalnetworksforpersonalitydetection
AT leichen psgcnpsycholinguisticgraphandsentimentsemanticfusedgraphconvolutionalnetworksforpersonalitydetection