Unlock instant, AI-driven research and patent intelligence for your innovation.
Network rumor recognition method and system
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A recognition method and rumor technology, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve the problem of unsatisfactory detection of rumors by neural network models
Active Publication Date: 2021-01-15
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
View PDF14 Cites 12 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, the current neural network rumor detection model mostly lies in learning better event features or semantic information, and the information dissemination of social mediain real life has a structural relationship, so the neural network model is not ideal for detecting rumors
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0059] figure 1 The flowchart of the network rumor identification method provided by Embodiment 1 of the present invention, such as figure 1 As shown, the methods include:
[0060] Step 101: Obtain a text feature matrix according to multiple texts containing rumor information.
[0061] Step 102: Construct a propagation graph structure, the nodes in the graph structure are multiple texts, and the adjacency matrix in the graph structure is the forwarding and commenting relationship of the rumor information among multiple texts.
[0062] Step 103: Constructing a graph convolutional neural network model; the input of the graph convolutional neural network model is the text feature matrix and the adjacency matrix, and the output of the graph convolutional neural network model is a rumor feature matrix.
[0063] Step 104: Train a neural network model according to the rumor feature matrix to obtain a rumor recognition model.
[0064] Step 105: Identify Internet rumors according to...
Embodiment 2
[0097] Figure 4 The principle diagram of the method for identifying network rumors provided by Embodiment 2 of the present invention, such as Figure 4 Shown:
[0098] (1) Take the twitter dataset as an example, which includes 1490 source microblogs, including 374 non-rumor microblogs, 370 false rumor microblogs, 374 uncertain rumor microblogs and 372 True rumor Weibo. Divide the data set into three parts: training set, validation set and test set, randomly select 10% as the validation set, the remaining 75% as the training set, and 25% as the test set.
[0099] rumor collection {r,w 1 ,w 2 ,w 3 ,w 4 ,w 5}, where r represents the source Weibo, w 1 ,w 2 ,w 3 ,w 4 ,w 5Indicates a retweet or related tweet. Remove all meaningless special symbols in the Weibo text, block out low-frequency words that appear less than twice, set all Weibo text content to 50 words, and fill in zeros before the text information when the text information is less than 50 words in length , ...
Embodiment 3
[0120] Figure 5 The systemblock diagram of the network rumor recognition system provided for Embodiment 3 of the present invention, such as Figure 5 As shown, the system includes:
[0121] The text feature matrix acquisition module 201 is configured to obtain a text feature matrix according to multiple texts containing rumor information.
[0122] The first construction module 202 is used to construct a propagation graph structure, the nodes in the graph structure are multiple texts, and the adjacency matrix in the graph structure is the forwarding of the rumor information among multiple texts and comment relationship.
[0123] The second building block 203 is used to construct a graph convolutional neural network model; the input of the graph convolutional neural network model is the text feature matrix and the adjacency matrix, and the output of the graph convolutional neural network model is rumors feature matrix.
[0124] The training module 204 is configured to trai...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
PUM
Login to View More
Abstract
The invention relates to a network rumor recognition method and system. The method comprises the steps of obtaining a text feature matrix according to multiple texts containing rumor information; constructing a propagation graph structure, nodes in the graph structure being a plurality of texts, and an adjacent matrix in the graph structure being a forwarding and commenting relationship of rumor information among the plurality of texts; constructing a graph convolutional neural network model, wherein the input of the graph convolutional neural network model is a text feature matrix and an adjacent matrix, and the output of the graph convolutional neural network model is a rumor feature matrix; training a neural network model according to the rumor feature matrix to obtain a rumor recognition model; and recognizing the network rumor according to the rumor recognition model. According to the invention, the graph convolutional neural network model is trained according to the forwarding and commenting relationship of the rumor among the plurality of texts, and the neural network model is trained according to the rumor feature matrix, so that wide and scattered propagation features of the rumor information are effectively captured, and the rumor information can be effectively identified.
Description
technical field [0001] The invention relates to the technical field of network rumor identification, in particular to a method and system for identifying network rumors. Background technique [0002] In the big data environment, online social networks are gradually integrated with people's life, entertainment and work. Social media has become a platform for people to share information and communicate. Its complex information, free and convenient dissemination, and great influence make it an important medium for public opinion to explode and heat up. Due to the lack of effective supervision, the proliferation of false information such as rumors will bring great threats and influences to the political, economic, cultural and other fields, and has become one of the main bottlenecks facing the development of many online social network applications. The task of social media rumor recognition has attracted strong attention from researchers in the fields of natural language proces...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More