Media forensics on social media platforms: a survey

Pasquini, Cecilia; Amerini, Irene; Boato, Giulia

doi:10.1186/s13635-021-00117-2

Cited by 44 publications

(27 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that the motivation of content creators can fluctuate within a fairly wide range, and cause the phenomenon of hierarchical regression (Gazit, 2021). The problem is exacerbated by the emergence of technologies that allow users with minimal technological knowledge to generate and distribute dangerous, antisocial, or even criminal content -such as the emergence of new methods of selflearning software that can create high-quality fake images and videos, for example, such software as Deepfakes (Amerini et al, 2021). Moreover, to manage social streams in the Internet space, "bot factories" are actively used today, both in manual mode (like the use of military personnel of the Armed Forces of Ukraine in Ukrainian IPS centers) and in an automated mode -in the form of automated computer online identities (Oehmer & Pedrazzi, 2020), the practice of using which in the domestic Internet space is not sufficiently legislatively regulated today.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Social Determination Factor In The Implementation Of State Information Policy Tasks

Krasnova¹

2021

European Proceedings of Social and Behavioural Sciences

View full text Add to dashboard Cite

The article examines some problems in the management of social processes, social adaptation and determination in solving a number of urgent tasks of the current state information policy of Russia. The main attention is paid to the analysis of the existing dependence of the Russian information society on foreign information resources and technologies, which qualitatively affect the state of information interests and information security of an individual, social groups and society as a whole. The author emphasizes the complexity and, at the same time, the need to update the management of the processes of social determination in the aspect of the proposed article. The emphasis is on the need to expand the segment of domestic digital resources, not only due to the qualitative improvement of content, but also quantitative superiority. The question of personality transformation is touched upon, the process goes into the sphere of technogenicity. The variety of platforms and resources ultimately leads to confusion, misunderstanding of who can be trusted, and in most cases the content is either very recreational in nature or does not meet basic quality requirements. This is why legislative regulation of the segment is necessary, especially in the area of content control. Also, the motivation of creators is equally important in this field. Digitalization is not only an important element in increasing the efficiency of the modern economy, but also a promising tool for public administration.

show abstract

Section: Resultsmentioning

confidence: 99%

“…The topic as a whole is quite well developed, especially within the framework of applied research of content: Kozlova (2020); Amerini et al (2021);Effah (2021). Also, the legal aspect of the problem field is being actively investigated - Cabaj et al (2021); Oehmer and Pedrazzi (2020).…”

Section: Problem Statementmentioning

confidence: 99%

Social Determination Factor In The Implementation Of State Information Policy Tasks

Krasnova¹

2021

European Proceedings of Social and Behavioural Sciences

View full text Add to dashboard Cite

show abstract

“…In doing so, social media is the latest phenomenon of interaction among people through virtual connected networks called social networking sites [38,39]. Social media is referred to as "computer-supported social networks" (CSSNs) [40], online social networking services [41], social networking sites (SNS) [42], social websites [43], social media platforms [44], virtual communities [45], and Web 2.0 [46]. Facebook is the most popular social media platform all over the world (except in restricted countries and territories) based on user statistics, and as of January 2021, the total number of users of Facebook was 2.740 billion, followed by YouTube (2.291 billion users) (Statistica, 2021) [47].…”

Section: Literature Review-circular Economy Social Media and Re-commercementioning

confidence: 99%

Re-Commerce to Ensure Circular Economy from Consumer Perspective

Arman

Mark‐Herbert

2021

Sustainability

View full text Add to dashboard Cite

Responsible consumption practice is crucial to minimizing waste as part of sustainable development (SDG 12). This can be achieved by extending product life in a cradle-to-cradle system as part of a circular economy. However, are consumers willing to extend product life by reusing materials? The phenomenon of re-commerce, where consumers sell products to each other (C2C), takes place in physical as well as web-based markets. This project focuses on enabling factors for re-commerce practices on Facebook among consumers in Bangladesh. A review of existing literature provided grounds for an empirical focus group study of Bangladeshi consumers. Using a social practice theory perspective in a thematic analysis shows that enabling factors in terms of technical competence, context-bound conditions influencing meanings such as socially accepted procedures, and practical practices relating to materials such as payment forms and logistics support, all serve as enabling or hindering factors. The study contributes to the understanding of conditions for re-commerce practices as part of a circular economy system where consumers are encouraged to engage in responsible consumption by extending product life cycles.

show abstract

“…Videos are typically compressed as sequence of groups of pictures (GOP), each of which is made by an alternation of three different kinds of frames: I-frames, which are not derived from any other frame and are independently encoded using a process similar to JPEG compression, and P-frames and B-frames, which are predictively encoded using motion estimation and compensation. While the algorithms used by social platforms are not known, all of these operations leave traces that can be detected [4,6,7,18,19] and, since they typically differ between different platforms [19][20][21], they can be used to distinguish between distinct social networks. According to the survey by Pasquini et al [21], we can identify two main possible steps in the digital life of a media object shared online, namely the acquisition and the upload.…”

Section: Related Workmentioning

confidence: 99%

“…While the algorithms used by social platforms are not known, all of these operations leave traces that can be detected [4,6,7,18,19] and, since they typically differ between different platforms [19][20][21], they can be used to distinguish between distinct social networks. According to the survey by Pasquini et al [21], we can identify two main possible steps in the digital life of a media object shared online, namely the acquisition and the upload. Initially, a real scene is captured through an acquisition device, then, a number of post-processing operations such as resizing, filtering, compressions, cropping, semantic manipulations may be applied.…”

Section: Related Workmentioning

confidence: 99%

Identification of Social-Media Platform of Videos through the Use of Shared Features

Maiano

Amerini

Celsi³

et al. 2021

J. Imaging

Self Cite

View full text Add to dashboard Cite

Videos have become a powerful tool for spreading illegal content such as military propaganda, revenge porn, or bullying through social networks. To counter these illegal activities, it has become essential to try new methods to verify the origin of videos from these platforms. However, collecting datasets large enough to train neural networks for this task has become difficult because of the privacy regulations that have been enacted in recent years. To mitigate this limitation, in this work we propose two different solutions based on transfer learning and multitask learning to determine whether a video has been uploaded from or downloaded to a specific social platform through the use of shared features with images trained on the same task. By transferring features from the shallowest to the deepest levels of the network from the image task to videos, we measure the amount of information shared between these two tasks. Then, we introduce a model based on multitask learning, which learns from both tasks simultaneously. The promising experimental results show, in particular, the effectiveness of the multitask approach. According to our knowledge, this is the first work that addresses the problem of social media platform identification of videos through the use of shared features.

show abstract

Media forensics on social media platforms: a survey

Cited by 44 publications

References 65 publications

Social Determination Factor In The Implementation Of State Information Policy Tasks

Social Determination Factor In The Implementation Of State Information Policy Tasks

Re-Commerce to Ensure Circular Economy from Consumer Perspective

Identification of Social-Media Platform of Videos through the Use of Shared Features

Contact Info

Product

Resources

About