Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph
Social media had a revolutionary impact because it provides an ideal platform for share information; however, it also leads to the publication and spreading of rumors. Existing rumor detection methods have relied on finding cues from only user-generated content, user profiles, or the structures of w...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/12/11/1806 |
| _version_ | 1797549164550160384 |
|---|---|
| author | Zunwang Ke Zhe Li Chenzhi Zhou Jiabao Sheng Wushour Silamu Qinglang Guo |
| author_facet | Zunwang Ke Zhe Li Chenzhi Zhou Jiabao Sheng Wushour Silamu Qinglang Guo |
| author_sort | Zunwang Ke |
| collection | DOAJ |
| description | Social media had a revolutionary impact because it provides an ideal platform for share information; however, it also leads to the publication and spreading of rumors. Existing rumor detection methods have relied on finding cues from only user-generated content, user profiles, or the structures of wide propagation. However, the previous works have ignored the organic combination of wide dispersion structures in rumor detection and text semantics. To this end, we propose KZWANG, a framework for rumor detection that provides sufficient domain knowledge to classify rumors accurately, and semantic information and a propagation heterogeneous graph are symmetry fused together. We utilize an attention mechanism to learn a semantic representation of text and introduce a GCN to capture the global and local relationships among all the source microblogs, reposts, and users. An organic combination of text semantics and propagating heterogeneous graphs is then used to train a rumor detection classifier. Experiments on Sina Weibo, Twitter15, and Twitter16 rumor detection datasets demonstrate the proposed model’s superiority over baseline methods. We also conduct an ablation study to understand the relative contributions of the various aspects of the method we proposed. |
| first_indexed | 2024-03-10T15:10:48Z |
| format | Article |
| id | doaj.art-3ed91fe187f549088f0131483e198a34 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-10T15:10:48Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-3ed91fe187f549088f0131483e198a342023-11-20T19:21:51ZengMDPI AGSymmetry2073-89942020-10-011211180610.3390/sym12111806Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous GraphZunwang Ke0Zhe Li1Chenzhi Zhou2Jiabao Sheng3Wushour Silamu4Qinglang Guo5College of Software, Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang Multilingual Information Technology Research Center, Xinjiang University, Urumqi 830046, ChinaCollege of Software, Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang Multilingual Information Technology Research Center, Xinjiang University, Urumqi 830046, ChinaShukutoku Japanese Language School, Tokyo 197-0804, JapanCollege of Software, Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang Multilingual Information Technology Research Center, Xinjiang University, Urumqi 830046, ChinaXinjiang Multilingual Information Technology Research Center, Xinjiang Laboratory of Multi-Language Information Technology, College of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaChina Academy of Electronics and Information Technology, National Engineering Laboratory for Risk Perception and Prevention (NEL-RPP), Beijing 100041, ChinaSocial media had a revolutionary impact because it provides an ideal platform for share information; however, it also leads to the publication and spreading of rumors. Existing rumor detection methods have relied on finding cues from only user-generated content, user profiles, or the structures of wide propagation. However, the previous works have ignored the organic combination of wide dispersion structures in rumor detection and text semantics. To this end, we propose KZWANG, a framework for rumor detection that provides sufficient domain knowledge to classify rumors accurately, and semantic information and a propagation heterogeneous graph are symmetry fused together. We utilize an attention mechanism to learn a semantic representation of text and introduce a GCN to capture the global and local relationships among all the source microblogs, reposts, and users. An organic combination of text semantics and propagating heterogeneous graphs is then used to train a rumor detection classifier. Experiments on Sina Weibo, Twitter15, and Twitter16 rumor detection datasets demonstrate the proposed model’s superiority over baseline methods. We also conduct an ablation study to understand the relative contributions of the various aspects of the method we proposed.https://www.mdpi.com/2073-8994/12/11/1806fake news detectionattentionGCNheterogeneous graphsocial networks |
| spellingShingle | Zunwang Ke Zhe Li Chenzhi Zhou Jiabao Sheng Wushour Silamu Qinglang Guo Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph Symmetry fake news detection attention GCN heterogeneous graph social networks |
| title | Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph |
| title_full | Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph |
| title_fullStr | Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph |
| title_full_unstemmed | Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph |
| title_short | Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph |
| title_sort | rumor detection on social media via fused semantic information and a propagation heterogeneous graph |
| topic | fake news detection attention GCN heterogeneous graph social networks |
| url | https://www.mdpi.com/2073-8994/12/11/1806 |
| work_keys_str_mv | AT zunwangke rumordetectiononsocialmediaviafusedsemanticinformationandapropagationheterogeneousgraph AT zheli rumordetectiononsocialmediaviafusedsemanticinformationandapropagationheterogeneousgraph AT chenzhizhou rumordetectiononsocialmediaviafusedsemanticinformationandapropagationheterogeneousgraph AT jiabaosheng rumordetectiononsocialmediaviafusedsemanticinformationandapropagationheterogeneousgraph AT wushoursilamu rumordetectiononsocialmediaviafusedsemanticinformationandapropagationheterogeneousgraph AT qinglangguo rumordetectiononsocialmediaviafusedsemanticinformationandapropagationheterogeneousgraph |