A Comparative Analysis of Active Learning for Rumor Detection on Social Media Platforms
In recent years, the ubiquity of social networks has transformed them into essential platforms for information dissemination. However, the unmoderated nature of social networks and the advent of advanced machine learning techniques, including generative models such as GPT and diffusion models, have...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/22/12098 |
| _version_ | 1827640802261598208 |
|---|---|
| author | Feng Yi Hongsheng Liu Huaiwen He Lei Su |
| author_facet | Feng Yi Hongsheng Liu Huaiwen He Lei Su |
| author_sort | Feng Yi |
| collection | DOAJ |
| description | In recent years, the ubiquity of social networks has transformed them into essential platforms for information dissemination. However, the unmoderated nature of social networks and the advent of advanced machine learning techniques, including generative models such as GPT and diffusion models, have facilitated the propagation of rumors, posing challenges to society. Detecting and countering these rumors to mitigate their adverse effects on individuals and society is imperative. Automatic rumor detection, typically framed as a binary classification problem, predominantly relies on supervised machine learning models, necessitating substantial labeled data; yet, the scarcity of labeled datasets due to the high cost of fact-checking and annotation hinders the application of machine learning for rumor detection. In this study, we address this challenge through active learning. We assess various query strategies across different machine learning models and datasets in order to offer a comparative analysis. Our findings reveal that active learning reduces labeling time and costs while achieving comparable rumor detection performance. Furthermore, we advocate for the use of machine learning models with nonlinear classification boundaries on complex environmental datasets for more effective rumor detection. |
| first_indexed | 2024-03-09T17:04:41Z |
| format | Article |
| id | doaj.art-97bb2683688f4f6d97b91ef4627dff4a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T17:04:41Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-97bb2683688f4f6d97b91ef4627dff4a2023-11-24T14:26:11ZengMDPI AGApplied Sciences2076-34172023-11-0113221209810.3390/app132212098A Comparative Analysis of Active Learning for Rumor Detection on Social Media PlatformsFeng Yi0Hongsheng Liu1Huaiwen He2Lei Su3School of Computer Science, Zhongshan Institute, University of Electronic Science and Technology of China, Zhongshan 528400, ChinaSchool of Computer Science, Zhongshan Institute, University of Electronic Science and Technology of China, Zhongshan 528400, ChinaSchool of Computer Science, Zhongshan Institute, University of Electronic Science and Technology of China, Zhongshan 528400, ChinaSchool of Computer Science, Zhongshan Institute, University of Electronic Science and Technology of China, Zhongshan 528400, ChinaIn recent years, the ubiquity of social networks has transformed them into essential platforms for information dissemination. However, the unmoderated nature of social networks and the advent of advanced machine learning techniques, including generative models such as GPT and diffusion models, have facilitated the propagation of rumors, posing challenges to society. Detecting and countering these rumors to mitigate their adverse effects on individuals and society is imperative. Automatic rumor detection, typically framed as a binary classification problem, predominantly relies on supervised machine learning models, necessitating substantial labeled data; yet, the scarcity of labeled datasets due to the high cost of fact-checking and annotation hinders the application of machine learning for rumor detection. In this study, we address this challenge through active learning. We assess various query strategies across different machine learning models and datasets in order to offer a comparative analysis. Our findings reveal that active learning reduces labeling time and costs while achieving comparable rumor detection performance. Furthermore, we advocate for the use of machine learning models with nonlinear classification boundaries on complex environmental datasets for more effective rumor detection.https://www.mdpi.com/2076-3417/13/22/12098rumor detectionactive learningactive learning query strategysocial networks |
| spellingShingle | Feng Yi Hongsheng Liu Huaiwen He Lei Su A Comparative Analysis of Active Learning for Rumor Detection on Social Media Platforms Applied Sciences rumor detection active learning active learning query strategy social networks |
| title | A Comparative Analysis of Active Learning for Rumor Detection on Social Media Platforms |
| title_full | A Comparative Analysis of Active Learning for Rumor Detection on Social Media Platforms |
| title_fullStr | A Comparative Analysis of Active Learning for Rumor Detection on Social Media Platforms |
| title_full_unstemmed | A Comparative Analysis of Active Learning for Rumor Detection on Social Media Platforms |
| title_short | A Comparative Analysis of Active Learning for Rumor Detection on Social Media Platforms |
| title_sort | comparative analysis of active learning for rumor detection on social media platforms |
| topic | rumor detection active learning active learning query strategy social networks |
| url | https://www.mdpi.com/2076-3417/13/22/12098 |
| work_keys_str_mv | AT fengyi acomparativeanalysisofactivelearningforrumordetectiononsocialmediaplatforms AT hongshengliu acomparativeanalysisofactivelearningforrumordetectiononsocialmediaplatforms AT huaiwenhe acomparativeanalysisofactivelearningforrumordetectiononsocialmediaplatforms AT leisu acomparativeanalysisofactivelearningforrumordetectiononsocialmediaplatforms AT fengyi comparativeanalysisofactivelearningforrumordetectiononsocialmediaplatforms AT hongshengliu comparativeanalysisofactivelearningforrumordetectiononsocialmediaplatforms AT huaiwenhe comparativeanalysisofactivelearningforrumordetectiononsocialmediaplatforms AT leisu comparativeanalysisofactivelearningforrumordetectiononsocialmediaplatforms |