Edge Convolutional Networks for Style Change Detection in Arabic Multi-Authored Text
The style change detection (SCD) task asks to find the positions of authors’ style changes within multi-authored texts. It has several application areas, such as forensics, cybercrime, and literary analysis. Since 2017, SCD solutions in English have been actively investigated. However, to the best o...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/12/6633 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849435397275254784 |
|---|---|
| author | Abeer Saad Alsheddi Mohamed El Bachir Menai |
| author_facet | Abeer Saad Alsheddi Mohamed El Bachir Menai |
| author_sort | Abeer Saad Alsheddi |
| collection | DOAJ |
| description | The style change detection (SCD) task asks to find the positions of authors’ style changes within multi-authored texts. It has several application areas, such as forensics, cybercrime, and literary analysis. Since 2017, SCD solutions in English have been actively investigated. However, to the best of our knowledge, this task has not yet been investigated in Arabic text. Moreover, most existing SCD solutions represent boundaries surrounding segments by concatenating them. This shallow concatenation may lose style patterns within each segment and also increase input lengths while several embedding models restrict these lengths. This study seeks to bridge these gaps by introducing an Edge Convolutional Neural Network for the Arabic SCD task (ECNN-ASCD) solution. It represents boundaries as standalone learnable parameters across layers based on graph neural networks. ECNN-ASCD was trained on an Arabic dataset containing three classes of instances according to difficulty level: easy, medium, and hard. The results show that ECNN-ASCD achieved a high <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mn>1</mn></msub></semantics></math></inline-formula> score of 0.9945%, 0.9381%, and 0.9120% on easy, medium, and hard instances, respectively. The ablation experiments demonstrated the effectiveness of ECNN-ASCD components. As the first publicly available solution for Arabic SCD, ECNN-ASCD would open the door for more active research on solving this task and contribute to boosting research in Arabic NLP. |
| format | Article |
| id | doaj-art-4bd6ff00c8784d4a9ea5749ba3ff87ad |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-4bd6ff00c8784d4a9ea5749ba3ff87ad2025-08-20T03:26:20ZengMDPI AGApplied Sciences2076-34172025-06-011512663310.3390/app15126633Edge Convolutional Networks for Style Change Detection in Arabic Multi-Authored TextAbeer Saad Alsheddi0Mohamed El Bachir Menai1Department of Computer Science, King Saud University, Riyadh 11451, Saudi ArabiaDepartment of Computer Science, King Saud University, Riyadh 11451, Saudi ArabiaThe style change detection (SCD) task asks to find the positions of authors’ style changes within multi-authored texts. It has several application areas, such as forensics, cybercrime, and literary analysis. Since 2017, SCD solutions in English have been actively investigated. However, to the best of our knowledge, this task has not yet been investigated in Arabic text. Moreover, most existing SCD solutions represent boundaries surrounding segments by concatenating them. This shallow concatenation may lose style patterns within each segment and also increase input lengths while several embedding models restrict these lengths. This study seeks to bridge these gaps by introducing an Edge Convolutional Neural Network for the Arabic SCD task (ECNN-ASCD) solution. It represents boundaries as standalone learnable parameters across layers based on graph neural networks. ECNN-ASCD was trained on an Arabic dataset containing three classes of instances according to difficulty level: easy, medium, and hard. The results show that ECNN-ASCD achieved a high <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mn>1</mn></msub></semantics></math></inline-formula> score of 0.9945%, 0.9381%, and 0.9120% on easy, medium, and hard instances, respectively. The ablation experiments demonstrated the effectiveness of ECNN-ASCD components. As the first publicly available solution for Arabic SCD, ECNN-ASCD would open the door for more active research on solving this task and contribute to boosting research in Arabic NLP.https://www.mdpi.com/2076-3417/15/12/6633natural language processingstyle change detectionmulti-authored documentsgraph neural networksArabic languagepretrained models |
| spellingShingle | Abeer Saad Alsheddi Mohamed El Bachir Menai Edge Convolutional Networks for Style Change Detection in Arabic Multi-Authored Text Applied Sciences natural language processing style change detection multi-authored documents graph neural networks Arabic language pretrained models |
| title | Edge Convolutional Networks for Style Change Detection in Arabic Multi-Authored Text |
| title_full | Edge Convolutional Networks for Style Change Detection in Arabic Multi-Authored Text |
| title_fullStr | Edge Convolutional Networks for Style Change Detection in Arabic Multi-Authored Text |
| title_full_unstemmed | Edge Convolutional Networks for Style Change Detection in Arabic Multi-Authored Text |
| title_short | Edge Convolutional Networks for Style Change Detection in Arabic Multi-Authored Text |
| title_sort | edge convolutional networks for style change detection in arabic multi authored text |
| topic | natural language processing style change detection multi-authored documents graph neural networks Arabic language pretrained models |
| url | https://www.mdpi.com/2076-3417/15/12/6633 |
| work_keys_str_mv | AT abeersaadalsheddi edgeconvolutionalnetworksforstylechangedetectioninarabicmultiauthoredtext AT mohamedelbachirmenai edgeconvolutionalnetworksforstylechangedetectioninarabicmultiauthoredtext |