PeakVis: a Visual Analysis Tool for Social Network Data and Video Broadcasts

Sanvido, Pedro; Kurtz, Gabriela Birnfeld; Teixeira, Carlos Roberto Gaspar; Wagner, Pedro P.; Leuck, Lorenzo P.; Silveira, Milene Selbach; Tietzmann, Roberto; Manssour, Isabel Harb

doi:10.1109/compsac51774.2021.00065

Cited by 2 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study claims that using SNA for visualisation purposes offers the possibility to scrutinise and visualise networks without necessarily inferring causal relationships to the underlying network structures. The benefits of visual analysis were also displayed in the PeakVis network visualisation tool developed by Sanvido et al [97], which analyses social media data, allowing users to identify relevant segments and grasp the subjects being discussed in real-time. Kucher et al [52] agree that SNA can be used for the visual analysis of social and text-based data.…”

Section: Social Network Analysismentioning

confidence: 99%

Anomaly detection using autoencoders with network analysis features

Ball

Drevin²

2023

ORiON

View full text Add to dashboard Cite

Fraudulent activity within a financial ecosystem often involves the coordinated efforts of several bad actors. Expressing the interactions between participants in a system as a mathematical graph allows researchers to apply social network analysis to understand the nature of these relationships better. This article proposes and extends a unified approach using an autoencoder to detect anomalies in a transactional setting. The methodology begins with a neural architecture search to determine a best autoencoder model architecture configuration. This is followed by a threshold optimisation process to find a reconstruction error that best discriminates between normal and anomalous classes. Gaussian scaling is applied to the raw anomaly scores in order to represent the output in an interpretable and universally transferable form. The unified approach is extended by selecting and including network metrics as features, for the purposes of producing a model that can detect anomalies from both standard transactional data and network data representing the relationships between users within a financial system. Applying SHAP on the model output highlighted the strongest contributing or offsetting network metric features for all anomalies detected. The PageRank and degree centrality network metrics were most significant in detecting anomalous instances within the data. Including network metrics in the feature space generated encouraging model performance results, leading to a potential low operational cost of fraud.

show abstract

Section: Social Network Analysismentioning

confidence: 99%

Anomaly detection using autoencoders with network analysis features

Ball

Drevin²

2023

ORiON

View full text Add to dashboard Cite

show abstract

“…And, in recent years, we've explored the visual analysis of the effects of audiovisual narratives on streaming data from social networking sites. This research resulted in PeakVis, an interactive tool that syncs a video recording with a responsive line graph representing the total number of tweets from each moment, the top messages, a dynamic word cloud, and a semantic graph showing word correlation [23]. The motivation is that nowadays, television broadcasts are expected to be accompanied by a stream of social media postings by the audience, mediating the asymmetrical relationship between the television network and spectators through commentary, humor, and criticism.…”

Section: A Visual Analysis Of Social Mediamentioning

confidence: 99%

DaVInt - Data Visualization and Interaction Lab

Manssour

Silveira²

2021

Anais Estendidos Da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021)

View full text Add to dashboard Cite

A multidisciplinary research project between Communication and Computer Science researchers gave rise to the Data Visualization and Interaction Lab, known as DaVInt lab. Officially created in 2017, DaVInt comprises students and researchers from Communication, and Computer Science and related areas. DaVInt's main research topics are related to visual analytics of social media, narrative visualization, and data science. However, computer vision projects and other individual initiatives are also developed. Its main contributions are divided into three main areas: scientific, through our publications; technological, making the results of our researches available to the community; and student education, through which we disseminate the area beyond academia.

show abstract

PeakVis: a Visual Analysis Tool for Social Network Data and Video Broadcasts

Cited by 2 publications

References 13 publications

Anomaly detection using autoencoders with network analysis features

Anomaly detection using autoencoders with network analysis features

DaVInt - Data Visualization and Interaction Lab

Contact Info

Product

Resources

About