Misleading or Falsification

Volkova, Svitlana; Jang, Jin Yea

doi:10.1145/3184558.3188728

Cited by 40 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, the combined approaches integrate content‐based approaches with social context‐based approaches. They are considered the most effective and the latest approach for dis/misinformation event detection from social media (Ruchansky et al, 2017; Shu et al, 2017; Volkova & Jang, 2018). For this reason, our proposed detection algorithm is also designed based on this combined approach.…”

Section: Related Workmentioning

confidence: 99%

A two‐step approach to detect and understand dismisinformation events occurring in social media: A case study with critical times

Yang

Chung

Singh

et al. 2023

Contingencies & Crisis Mgmt

View full text Add to dashboard Cite

This article describes a novel two‐step approach of detecting and understanding dis/misinformation events in social media that occur during disasters and crisis events. To detect false news events, we designed a deep learning‐based detection algorithm and then trained it with a transfer learning scheme so that the algorithm could decide whether a given group of rumor‐related tweets is a dis/misinformation event. For understanding how dis/misinformation was diffused in social networks and identifying those who are responsible for creating and consuming false information, we present DismisInfoVis, which consists of various visualisations, including a social network graph, a map, line charts, pie charts, and bar charts. By integrating these deep learning and multi‐view visualisation techniques, we could gain a deeper insight into dis/misinformation events in social media from multiple angles. We describe in detail the implementation, training process, and performance evaluations of the detection algorithm and the design and utilization of DismisInfoVis for dis/misinformation data analyses. We hope that this study will contribute to improving the quality of information generated and shared on social media during critical times, eventually helping both the affected and the general public recover from the impacts of disasters and crisis events.

show abstract

Section: Related Workmentioning

confidence: 99%

A two‐step approach to detect and understand dismisinformation events occurring in social media: A case study with critical times

Yang

Chung

Singh

et al. 2023

Contingencies & Crisis Mgmt

View full text Add to dashboard Cite

show abstract

“…Detecting fake news on social media is a popular research topic, studied in supervised learning (Hassan et al, 2017;Pérez-Rosas et al, 2018;Volkova and Jang, 2018;Ma et al, 2018;Shu et al, 2019a,b;Kim et al, 2019), Graphs (Han et al, 2020;Li et al, 2022), zero-shot (Wright et al, 2022, dialogue (Gupta et al, 2022), cross-domain (Huang et al, 2021;Zhu et al, 2022a,b;Mosallanezhad et al, 2022), and low-resource (Lin et al, 2022) settings.…”

Section: Related Workmentioning

confidence: 99%

Interactively Learning Social Media Representations Improves News Source Factuality Detection

Mehta,

Goldwasser

2023

Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

View full text Add to dashboard Cite

The rise of social media has enabled the widespread propagation of fake news, text that is published with an intent to spread misinformation and sway beliefs. Rapidly detecting fake news, especially as new events arise, is important to prevent misinformation.While prior works have tackled this problem using supervised learning systems, automatedly modeling the complexities of the social media landscape that enables the spread of fake news is challenging. On the contrary, having humans fact check all news is not scalable. Thus, in this paper, we propose to approach this problem interactively, where humans can interact to help an automated system learn a better social media representation quality. On real world events, our experiments show performance improvements in detecting factuality of news sources, even after few human interactions.

show abstract

“…Trabalhos relacionados ao grupo (i) geralmente analisam aspectos léxicos, sintáticos e semânticos presentes no texto da notícia. Abordagens sintáticas envolvem contagens de palavras (sujeitos, verbos, adjetivos), presença e frequência de padrões ou expressões específicas e análises de legibilidade do texto (número de caracteres, palavras complexas, palavras longas, número de sílabas, número de parágrafos) (KSIENIEWICZ et al, 2023;SANTOS;REIS et al, 2019;JANG, 2018;PÉREZ-ROSAS et al, 2017). Outros indicadores de conteúdo falso são pausalidade, incerteza, expressividade, redundância e especificidade .…”

Section: Detecção De Notícias Falsasunclassified

Detecção de notícias falsas usando poucos dados positivos rotulados

Souza

View full text Add to dashboard Cite

Agradeço a Deus, que sempre me deu coragem e bom ânimo para seguir em frente. Agradeço aos meus pais, Jorge e Marli, minha base sólida, por me ensinarem tantos valores e me apoiarem em todas as decisões importantes. Cada conquista ao longo desta jornada é reflexo da dedicação e carinho que sempre recebi de vocês. Agradeço ao meu irmão, Gabriel, que morou comigo parte do período de doutorado, sendo um apoio em dias difíceis. Agradeço também ao meu parceiro, Thiago, que segurou minha mão em todo o percurso, e mesmo com a distância, sempre me incentivou a cumprir meus objetivos.

show abstract

Misleading or Falsification

Cited by 40 publications

References 33 publications

A two‐step approach to detect and understand dismisinformation events occurring in social media: A case study with critical times

A two‐step approach to detect and understand dismisinformation events occurring in social media: A case study with critical times

Interactively Learning Social Media Representations Improves News Source Factuality Detection

Detecção de notícias falsas usando poucos dados positivos rotulados

Contact Info

Product

Resources

About