http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113111267-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_db9efde660b78f98b102046e09d07ab7 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-9536 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2415 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F40-216 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F40-216 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F16-9536 |
filingDate | 2021-04-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_bd383fc3b5ebc5590919ea5ac450d477 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_649929e603b8943943ce1f45d31db2e4 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1206eb4f35af17245ab239d6196670a7 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f141939572c2099ae7d737fb2e4f846e |
publicationDate | 2021-07-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-113111267-A |
titleOfInvention | A multi-task rumor detection method based on bidirectional propagation graph |
abstract | The invention discloses a multi-task rumor detection method based on a bidirectional propagation graph, which can be used for rumor detection of social network posts and position detection of comment information. The invention firstly generates a text feature matrix, a user feature matrix and a text statistical feature matrix according to the content of the rumor post, then constructs the bidirectional propagation graph of the rumor, extracts the propagation feature of the rumor by calculating the bidirectional graph convolution and performing root node feature enhancement, and finally extracts the propagation feature of the rumor. After average pooling and feature integration of the propagation features, a softmax classifier is trained to obtain the results of rumor detection and position detection. The present invention can effectively acquire the sequence propagation features and breadth spreading features of rumors, and introduce the position detection of user comments as an auxiliary task, thereby improving the generalization of the model and further improving the accuracy of the rumor detection task. |
priorityDate | 2021-04-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID19909 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID457559389 |
Total number of triples: 25.