Rumor Detection on Social Media: Datasets, Methods and Opportunities

Li, Quanzhi; Zhang, Qiong; Si, Luo; Liu, Yingchi

doi:10.18653/v1/d19-5008

Cited by 48 publications

(27 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We have performed a case study of rumor diffusion on Twitter during a disaster rather than a general study of rumor diffusion. We are planning to apply the proposed method to another rumor dataset [43] and systematically investigate temporal patterns in topic diversity toward the development of a practical rumor detection algorithm.…”

Section: Discussionmentioning

confidence: 99%

Analyzing temporal patterns of topic diversity using graph clustering

et al. 2020

View full text Add to dashboard Cite

During a disaster, social media can be both a source of help and of danger: Social media has a potential to diffuse rumors, and officials involved in disaster mitigation must react quickly to the spread of rumor on social media. In this paper, we investigate how topic diversity (i.e., homogeneity of opinions in a topic) depends on the truthfulness of a topic (whether it is a rumor or a non-rumor) and how the topic diversity changes in time after a disaster. To do so, we develop a method for quantifying the topic diversity of the tweet data based on text content. The proposed method is based on clustering a tweet graph using Data polishing that automatically determines the number of subtopics. We perform a case study of tweets posted after the East Japan Great Earthquake on March 11, 2011. We find that rumor topics exhibit more homogeneity of opinions in a topic during diffusion than non-rumor topics. Furthermore, we evaluate the performance of our method and demonstrate its improvement on the runtime for data processing over existing methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Analyzing temporal patterns of topic diversity using graph clustering

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Indeed, on account of time limits of Twitter API sometimes researchers focus on small data samples [8] or on biased data. For instance, most recent studies [16] on rumors detection focus only on tweets published in English and do not consider those disseminated in other languages which should be useful to improve the accuracy of detection. Thus, despite the important time required to collect the data and then analyze it certain works are not presented in conferences because the results of studies are too specific and can not be generalized.…”

Section: Consequences On Researchers Activitiesmentioning

confidence: 99%

TwiScraper: A Collaborative Project to Enhance Twitter Data Collection

Henry

2021

Proceedings of the 14th ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

In past years several works have noted that Twitter data are essential in diverse fields and may have a lot of applications. Nevertheless, the API proposed by Twitter sternly restricts access to public data generated by users. These restrictions have the consequences of greatly slowing down the contributions of researchers and of limiting their scope. In this paper we introduce TwiScraper, a collaborative project to enhance Twitter data collection by scraping methods. We present a module allowing user-centered data collection: Twi-FFN.

show abstract

“…Identifying misinformation is a chief concern in infodemiology via infoveillance, not to mention in other areas of society like sociology and politics. Methods that use the probabilistic and lexical features of text in order to determine whether they represent misinformation (Li et al, 2019) abound. These methods depend on datasets that contain messages which have already been labelled misinformation by experts a priori.…”

Section: Value Of Misinformationmentioning

confidence: 99%

In.To. COVID-19 Socio-epidemiological Co-causality

Galbraith

Convertino

et al. 2021

Preprint

View full text Add to dashboard Cite

Social media can forecast disease dynamics, but infoveillance remains focused on infection spread, with little consideration of media content reliability and its relationship to behavior-driven epidemiological outcomes. Sentiment-encoded social media indicators have been poorly developed for expressed text to forecast healthcare pressure and infer population risk perception patterns. Here we introduce Infodemic Tomography (InTo) as the first web-based interactive infoveillance cybertechnology that forecasts and visualizes spatio-temporal sentiments and healthcare pressure as a function of social media positivity (i.e., Twitter here), considering both epidemic information and potential misinformation. Information spread is measured on volume and retweets and the Value of Misinformation (VoMi) is introduced as the impact on forecast accuracy where misinformation has the highest dissimilarity in information dynamics. We validate InTo for COVID-19 in New Delhi and three other SE Asian cities. We forecast weekly hospitalization and cases using ARIMA models and interpolate spatial hospitalization using geostatistical kriging on inferred risk perception curves between tweet positivity and epidemiological outcomes. Geospatial tweet positivity tracks accurately ~60% of hospitalizations and forecasts hospitalization risk hotspots along risk aversion gradients. VoMi is higher for risk-prone areas and time periods, where misinformation has the highest predictability, with high incidence and positivity manifesting popularity-seeking social dynamics. Hospitalization gradients, VoMi, effective healthcare pressure and spatial model-data gaps can be used to predict hospitalization fluxes, misinformation, capacity gaps and surveillance uncertainty. Thus, InTo is a participatory instrument to better prepare and respond to public health crises by extracting and combining salient epidemiological and social surveillance at any desired space-time scale.

show abstract

Rumor Detection on Social Media: Datasets, Methods and Opportunities

Cited by 48 publications

References 32 publications

Analyzing temporal patterns of topic diversity using graph clustering

Analyzing temporal patterns of topic diversity using graph clustering

TwiScraper: A Collaborative Project to Enhance Twitter Data Collection

In.To. COVID-19 Socio-epidemiological Co-causality

Contact Info

Product

Resources

About