Pushtext-level social media rumor detection method

Abstract

The invention relates to a pushtext-level social media rumor detection method. Modeling is directly started from the sentences of the event, and features are extracted from the words of each sentences. Compared with a model based on manual features, the method has the advantages that the features from concrete to abstraction can be automatically extracted, manual intervention is reduced, and the method is more convenient to use. And meanwhile, objective and targeted characteristics can be automatically obtained, so that the model can be better applied to complex scenes such as social media. Compared with GRU and CNN models, the method has the advantage that the interference of non-standard network terms on rumor event detection can be relieved as much as possible. According to the method,different life cycles are divided by utilizing the change of the event popularity, so that each life cycle is more interpretable, and meanwhile, the sentences in each life cycle are more consistent. According to the invention, in the rumor event detection of social media, higher accuracy is obtained, and the rumor event can be detected at the earlier stage of event development.

Description

technical field [0001] The invention belongs to the field of deep learning and natural language processing in machine learning, and more specifically, relates to a tweet-level social media rumor detection method. Background technique [0002] Psychology, sociology, and communication circles generally define a rumor as a statement or representation that is unsubstantiated or intentionally false. Therefore, in this case, it is an important task to effectively and quickly identify rumors in social media. [0003] In previous related research work, scholars have proposed many methods to detect whether a single tweet is a rumor. A tweet usually only has less contextual information, and since rumors can usually be stated in the same way as non-rumors, rumor detection on tweets faces the problem of insufficient information. At the same time, usually Internet rumors will be widely disseminated on social media to form an event, so the rumor detection of events will be more practica...

AI Technical Summary

Problems solved by technology

However, these models have some drawbacks

First, GRU, a deep learning model based on a recurrent neural network, tends to pay more attention to the final input, but there is no evidence that the last few life cycles are more helpful for rumor event monitoring

The second point is that the language used by users in social media is not standardized, and there are many new words and wrong expressions on the Internet. Therefore, it is difficult for traditional word segmentation methods to accurately divide each word.

At the same time, they use the unsupervised method of word frequency-reverse file frequency or paragraph vector to construct the life cycle vector, so that their model cannot correct the impact of word segmentation errors through supervised learning, so that their model cannot be further improved. Accuracy of rumor event detection

The third point is that they use the same time interval to divide the life cycle of events. Although such a modeling method is simple, it is not interpretable, and it cannot guarantee the consistency of tweets in each cycle using rumor detection.

Images