Design and analysis of a large-scale COVID-19 tweets dataset

Applied Intelligence, Год журнала: 2020, Номер 51(5), С. 2790 - 2804

Опубликована: Ноя. 6, 2020

Язык: Английский

---

Misinformation, manipulation, and abuse on social media in the era of COVID-19

Journal of Computational Social Science, Год журнала: 2020, Номер 3(2), С. 271 - 277

Опубликована: Ноя. 1, 2020

The COVID-19 pandemic represented an unprecedented setting for the spread of online misinformation, manipulation, and abuse, with potential to cause dramatic real-world consequences. aim this special issue was collect contributions investigating issues such as emergence infodemics, conspiracy theories, automation, harassment on onset coronavirus outbreak. Articles in collection adopt a diverse range methods techniques, focus study narratives that fueled diffusion patterns global news sentiment, hate speech social bot interference, multimodal Chinese propaganda. diversity methodological scientific approaches undertaken aforementioned articles demonstrates interdisciplinarity these issues. In turn, crucial endeavors might anticipate growing trend studies where models, techniques will be combined tackle different aspects abuse.

Язык: Английский

---

Cross-SEAN: A cross-stitch semi-supervised neural attention model for COVID-19 fake news detection

Applied Soft Computing, Год журнала: 2021, Номер 107, С. 107393 - 107393

Опубликована: Апрель 16, 2021

Язык: Английский

---

Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society

Опубликована: Янв. 1, 2021

Firoj Alam, Shaden Shaar, Fahim Dalvi, Hassan Sajjad, Alex Nikolov, Hamdy Mubarak, Giovanni Da San Martino, Ahmed Abdelali, Nadir Durrani, Kareem Darwish, Abdulaziz Al-Homaid, Wajdi Zaghouani, Tommaso Caselli, Gijs Danoe, Friso Stolk, Britt Bruntink, Preslav Nakov. Findings of the Association for Computational Linguistics: EMNLP 2021.

Язык: Английский

---

TweetsCOV19 - A Knowledge Base of Semantically Annotated Tweets about the COVID-19 Pandemic

Опубликована: Окт. 19, 2020

Publicly available social media archives facilitate research in the sciences and provide corpora for training testing a wide range of machine learning natural language processing methods. With respect to recent outbreak Coronavirus disease 2019 (COVID-19), online discourse on Twitter reflects public opinion perception related pandemic itself as well mitigating measures their societal impact. Understanding such discourse, its evolution, interdependencies with real-world events or (mis)information can foster valuable insights. On other hand, are crucial facilitators computational methods addressing tasks sentiment analysis, event detection, entity recognition. However, obtaining, archiving, semantically annotating large amounts tweets is costly. In this paper, we describe TweetsCOV19, publicly knowledge base currently more than 8 million tweets, spanning October - April 2020. Metadata about extracted entities, hashtags, user mentions, sentiments, URLs exposed using established RDF/S vocabularies, providing an unprecedented discovery tasks. Next description dataset extraction annotation process, present initial analysis use cases corpus.

Язык: Английский

---

Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms

Proceedings of the International AAAI Conference on Web and Social Media, Год журнала: 2021, Номер 15, С. 913 - 922

Опубликована: Май 22, 2021

With the outbreak of COVID-19 pandemic, people turned to social media read and share timely information including statistics, warnings, advice, inspirational stories. Unfortunately, alongside all this useful information, there was also a new blending medical political misinformation disinformation, which gave rise first global infodemic. While fighting infodemic is typically thought in terms factuality, problem much broader as malicious content includes not only fake news, rumors, conspiracy theories, but promotion cures, panic, racism, xenophobia, mistrust authorities, among others. This complex that needs holistic approach combining perspectives journalists, fact-checkers, policymakers, government entities, platforms, society whole. mind, we define an annotation schema detailed instructions reflect these perspectives. We further deploy multilingual platform, issue call arms research community beyond join fight by supporting our crowdsourcing efforts. perform initial annotations using schema, experiments demonstrated sizable improvements over baselines.

Язык: Английский

---

Fake news detection: a survey of evaluation datasets

PeerJ Computer Science, Год журнала: 2021, Номер 7, С. e518 - e518

Опубликована: Июнь 18, 2021

Fake news detection has gained increasing importance among the research community due to widespread diffusion of fake through media platforms. Many dataset have been released in last few years, aiming assess performance methods. In this survey, we systematically review twenty-seven popular datasets for by providing insights into characteristics each and comparative analysis them. A characterization composed eleven extracted from surveyed is provided, along with a set requirements comparing building new datasets. Due ongoing interest topic, results are valuable many researchers guide selection or definition suitable evaluating their

Язык: Английский

---

Integrating remote sensing and social sensing for flood mapping

Remote Sensing Applications Society and Environment, Год журнала: 2022, Номер 25, С. 100697 - 100697

Опубликована: Янв. 1, 2022

Flood events cause substantial damage to infrastructure and disrupt livelihoods. Timely monitoring of flood extent helps authorities identify severe impacts plan relief operations. Remote sensing through satellite imagery is an effective method flooded areas. However, critical contextual information about the severity structural or urgent needs affected population cannot be obtained from remote alone. On other hand, social microblogging sites can potentially provide useful directly eyewitnesses people. Therefore, this paper explores integration data derive informed maps. For purpose, we employ state-of-the-art deep learning methods process heterogeneous four case-study areas, including two urban regions Somalia India coastal Italy The Bahamas. side, observe that models perform generally better than Otsu in water prediction. example, for highly areas India, U-Net achieves F1-scores (0.471 0.310, respectively) (0.297 0.251, respectively). Similarly, FCN yields a F1-score (0.128) (0.083) while on par Bahamas (0.102 0.105, Then, add layers representing relevant tweet text images posted highlight different ways these sources complement each other. Our extensive analyses reveal several valuable insights. In particular, three types signals: (i) confirmatory signals both sources, which puts greater confidence specific region flooded, (ii) complementary requests, disaster impact reports situational information, (iii) novel when do not overlap unique information.

Язык: Английский

---

TBCOV: Two Billion Multilingual COVID-19 Tweets with Sentiment, Entity, Geo, and Gender Labels

Data, Год журнала: 2022, Номер 7(1), С. 8 - 8

Опубликована: Янв. 10, 2022

The widespread usage of social networks during mass convergence events, such as health emergencies and disease outbreaks, provides instant access to citizen-generated data that carry rich information about public opinions, sentiments, urgent needs, situational reports. Such can help authorities understand the emergent situation react accordingly. Moreover, media plays a vital role in tackling misinformation disinformation. This work presents TBCOV, large-scale Twitter dataset comprising more than two billion multilingual tweets related COVID-19 pandemic collected worldwide over continuous period one year. More importantly, several state-of-the-art deep learning models are used enrich with important attributes, including sentiment labels, named-entities (e.g., mentions persons, organizations, locations), user types, gender information. Last but not least, geotagging method is proposed assign country, state, county, city tweets, enabling myriad analysis tasks real-world issues. Our trend analyses reveal interesting insights confirm TBCOV's broad coverage topics.

Язык: Английский

---

Classification aware neural topic model for COVID-19 disinformation categorisation

PLoS ONE, Год журнала: 2021, Номер 16(2), С. e0247086 - e0247086

Опубликована: Фев. 18, 2021

The explosion of disinformation accompanying the COVID-19 pandemic has overloaded fact-checkers and media worldwide, brought a new major challenge to government responses worldwide. Not only is creating confusion about medical science amongst citizens, but it also amplifying distrust in policy makers governments. To help tackle this, we developed computational methods categorise disinformation. categories could be used for a) focusing fact-checking efforts on most damaging kinds disinformation; b) guiding who are trying deliver effective public health messages counter effectively This paper presents: 1) corpus containing what currently largest available set manually annotated categories; 2) classification-aware neural topic model (CANTM) designed category classification discovery; 3) an extensive analysis with respect time, volume, false type, type origin source.

Язык: Английский

---