Microblog-HAN: A micro-blog rumor detection model based on heterogeneous graph attention network
Although social media has highly facilitated people’s daily communication and dissemination of information, it has unfortunately been an ideal hotbed for the breeding and dissemination of Internet rumors. Therefore, automatically monitoring rumor dissemination in the early stage is of great practica...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9004763/?tool=EBI |
| _version_ | 1811332156016820224 |
|---|---|
| author | Bei Bi Yaojun Wang Haicang Zhang Yang Gao |
| author_facet | Bei Bi Yaojun Wang Haicang Zhang Yang Gao |
| author_sort | Bei Bi |
| collection | DOAJ |
| description | Although social media has highly facilitated people’s daily communication and dissemination of information, it has unfortunately been an ideal hotbed for the breeding and dissemination of Internet rumors. Therefore, automatically monitoring rumor dissemination in the early stage is of great practical significance. However, the existing detection methods fail to take full advantage of the semantics of the microblog information propagation graph. To address this shortcoming, this study models the information transmission network of a microblog as a heterogeneous graph with a variety of semantic information and then constructs a Microblog-HAN, which is a graph-based rumor detection model, to capture and aggregate the semantic information using attention layers. Specifically, after the initial textual and visual features of posts are extracted, the node-level attention mechanism combines neighbors of the microblog nodes to generate three groups of node embeddings with specific semantics. Moreover, semantic-level attention fuses different semantics to obtain the final node embedding of the microblog, which is then used as a classifier’s input. Finally, the classification results of whether the microblog is a rumor or not are obtained. The experimental results on two real-world microblog rumor datasets, Weibo2016 and Weibo2021, demonstrate that the proposed Microblog-HAN can detect microblog rumors with an accuracy of over 92%, demonstrating its superiority over the most existing methods in identifying rumors from the view of the whole information transmission graph. |
| first_indexed | 2024-04-13T16:32:28Z |
| format | Article |
| id | doaj.art-75b76a4217234125a6d15559d41b922e |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-13T16:32:28Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-75b76a4217234125a6d15559d41b922e2022-12-22T02:39:32ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01174Microblog-HAN: A micro-blog rumor detection model based on heterogeneous graph attention networkBei BiYaojun WangHaicang ZhangYang GaoAlthough social media has highly facilitated people’s daily communication and dissemination of information, it has unfortunately been an ideal hotbed for the breeding and dissemination of Internet rumors. Therefore, automatically monitoring rumor dissemination in the early stage is of great practical significance. However, the existing detection methods fail to take full advantage of the semantics of the microblog information propagation graph. To address this shortcoming, this study models the information transmission network of a microblog as a heterogeneous graph with a variety of semantic information and then constructs a Microblog-HAN, which is a graph-based rumor detection model, to capture and aggregate the semantic information using attention layers. Specifically, after the initial textual and visual features of posts are extracted, the node-level attention mechanism combines neighbors of the microblog nodes to generate three groups of node embeddings with specific semantics. Moreover, semantic-level attention fuses different semantics to obtain the final node embedding of the microblog, which is then used as a classifier’s input. Finally, the classification results of whether the microblog is a rumor or not are obtained. The experimental results on two real-world microblog rumor datasets, Weibo2016 and Weibo2021, demonstrate that the proposed Microblog-HAN can detect microblog rumors with an accuracy of over 92%, demonstrating its superiority over the most existing methods in identifying rumors from the view of the whole information transmission graph.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9004763/?tool=EBI |
| spellingShingle | Bei Bi Yaojun Wang Haicang Zhang Yang Gao Microblog-HAN: A micro-blog rumor detection model based on heterogeneous graph attention network PLoS ONE |
| title | Microblog-HAN: A micro-blog rumor detection model based on heterogeneous graph attention network |
| title_full | Microblog-HAN: A micro-blog rumor detection model based on heterogeneous graph attention network |
| title_fullStr | Microblog-HAN: A micro-blog rumor detection model based on heterogeneous graph attention network |
| title_full_unstemmed | Microblog-HAN: A micro-blog rumor detection model based on heterogeneous graph attention network |
| title_short | Microblog-HAN: A micro-blog rumor detection model based on heterogeneous graph attention network |
| title_sort | microblog han a micro blog rumor detection model based on heterogeneous graph attention network |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9004763/?tool=EBI |
| work_keys_str_mv | AT beibi microbloghanamicroblogrumordetectionmodelbasedonheterogeneousgraphattentionnetwork AT yaojunwang microbloghanamicroblogrumordetectionmodelbasedonheterogeneousgraphattentionnetwork AT haicangzhang microbloghanamicroblogrumordetectionmodelbasedonheterogeneousgraphattentionnetwork AT yanggao microbloghanamicroblogrumordetectionmodelbasedonheterogeneousgraphattentionnetwork |