Extreme User and Political Rumor Detection on Twitter

Chang, Cheng; Zhang, Yihong; Szabo, Claudia; Sheng, Quan Z.

doi:10.1007/978-3-319-49586-6_54

Cited by 33 publications

(20 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several features relating to the content, crowd opinion and post propagation were used. Chang et al [20] put the emphasis on the characteristics of users who post the rumours to determine the veracity. Tong et al [21] aimed at curtailing false rumour spread rather than marking tweets as true or false.…”

Section: Related Workmentioning

confidence: 99%

Rumour verification through recurring information and an inner-attention mechanism

Aker

Sliwa

Dalvi

et al. 2019

Online Social Networks and Media

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Rumour verification through recurring information and an inner-attention mechanism

Aker

Sliwa

Dalvi

et al. 2019

Online Social Networks and Media

View full text Add to dashboard Cite

show abstract

“…As a result, the authenticity of some microblogs is in doubt. It is necessary to strengthen the discrimination of rumors and false information in microblogs [38,39].…”

Section: Discussionmentioning

confidence: 99%

Information Detection for the Process of Typhoon Events in Microblog Text: A Spatio-Temporal Perspective

Zhang

Huai

et al. 2021

IJGI

View full text Add to dashboard Cite

Typhoon is one of the most destructive natural disasters in the world. Real-time information on the process of typhoon events serves as important reference for disaster emergency. In the era of big data, microblog text has been gradual applied to the prevention, preparation, response, and recovery of disaster management. However, previous studies mostly focused on the acquisition of different disaster information in microblog text, while ignoring the structural integration of this fragmented information, and thus cannot reflect the dynamic process of typhoon events. In this paper, a typhoon event information model (TEIM) considering the multi-granularity and dynamic characteristics of information is constructed from the spatio-temporal perspective. On the basis of extracting the information elements of typhoon events from microblog text, a process-oriented information aggregation method (TEPIA) is proposed to provide an ordered information resource for detecting the evolution process of typhoon events. Based on the case study of typhoon “Lekima” event using Sina Weibo, the results show that the method proposed in this paper can comprehensively detect the information of different objects on any spatio-temporal node during the process of typhoon events, which is beneficial to mining disaster emergencies in small scale from microblog text.

show abstract

“…Results indicated the features hold a good discriminative power in detecting rumor for a specific topic dataset, reaching an overall accuracy of 96%. Unlike previous studies by using above features for rumor events detection directly, Chang et al [25] firstly determined the ''extreme users'' based on these various features and heuristics, and then judged the truth-fulness of tweets according to the number of the extreme users involved. The extensive experiments reported accurate detection with precision and recall both above 80%.…”

Section: A Traditional Ml-based Approachesmentioning

confidence: 99%

Rumor Events Detection From Chinese Microblogs via Sentiments Enhancement

et al. 2019

View full text Add to dashboard Cite

The convenience of social media in communication and information dissemination has made it an ideal place for spreading rumor events, which raises a higher requirement for automatic debunking of rumor events. Meanwhile, the traditional rumor classification approaches relying on manual labeled features have to face a daunting number of manual efforts. In general, when facing a dubious claim, people can authenticate and verify the realness of an event with the contents of continuous posts, such as source credibility, public sentiments, propagation structures, and so on. In this paper, we pay more attention to the emotional expressions of posts host, especially the fine-grained sentiments, which are effective for rumor events detection. Thus, this paper presents a novel two-layer GRU model for rumor events detection based on a Sentiment Dictionary (SD) and a dynamic time series (DTS) algorithm, named as SD-DTS-GRU. The model learns continuous representations of microblog events in a better manner by making use of the SD to identify fine-grained human emotional expressions of each event and retaining the time distribution of social events by the DTS algorithm. The experimental results on Sina Weibo datasets show that our model achieves a high accuracy of 95.2% and demonstrate that our proposed SD-DTS-GRU model outperforms latest explorations on rumor events detection. INDEX TERMS Rumor events detection, sentiment dictionary, dynamic time series, GRU, online social networks.

show abstract

Extreme User and Political Rumor Detection on Twitter

Cited by 33 publications

References 14 publications

Rumour verification through recurring information and an inner-attention mechanism

Rumour verification through recurring information and an inner-attention mechanism

Information Detection for the Process of Typhoon Events in Microblog Text: A Spatio-Temporal Perspective

Rumor Events Detection From Chinese Microblogs via Sentiments Enhancement

Contact Info

Product

Resources

About