BRNADS: Big data real-time node anomaly detection in social networks

Manjunatha, H.C.; Mohanasundaram, R.

doi:10.1109/icisc.2018.8398937

Cited by 9 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many authors are doing research on social network datasets and proposing various anomaly detection mechanisms to identify anomalous activities in both static and dynamic growing social networks. 25 In this study, the current popular microblog data set is used for experiments. Based on the Big Five Model of Personality, 336 questions from 30 dimensions were evaluated for users, and the final test results are obtained.…”

Section: Source Of Datamentioning

confidence: 99%

RETRACTED: The prediction model of personality in social networks by using data mining deep learning algorithm and random walk model

Zhu

2020

International Journal of Electrical Engineering & Education

View full text Add to dashboard Cite

The objective is to predict and analyze the behaviors of users in the social network platform by using the personality theory and computational technologies, thereby acquiring the personality characteristics of social network users more effectively. First, social network data are analyzed, which finds that the type of text data marks the majority. By using data mining technology, the raw data of numerous social network users can be obtained. Based on the random walk model, the data information of the text status of social network users is analyzed, and a user personality prediction method integrating multi-label learning is proposed. In addition, the online social network platform Weibo is taken as the research object. The blog information of Weibo users is obtained through crawler technology. Then, the users are labeled in accordance with personality characteristics. The Pearson correlation coefficient is used to evaluate the relation between the user personality characteristics and the user behavior characteristics of the Weibo users. The correlation between the network behaviors and personality characteristics of Weibo users is analyzed, and the scientificity of the prediction method is verified by the Big Five Model of Personality. By applying relevant technologies and algorithms of data mining and deep learning, the learning ability of neural networks on data characteristics can be improved. In terms of performance on analyzing text information of social network users, the user personality prediction method of integrated multi-label learning based on the random walk model has a large advantage. For the problem of personality prediction of social network users, through combining data mining technology and deep neural network technology in deep learning, the data processing results of social network user behaviors are more accurate.

show abstract

Section: Source Of Datamentioning

confidence: 99%

RETRACTED: The prediction model of personality in social networks by using data mining deep learning algorithm and random walk model

Zhu

2020

International Journal of Electrical Engineering & Education

View full text Add to dashboard Cite

show abstract

“…The results show that the proposed approach improves computation efficiency and scalability for principal score calculation. Manjunatha et al [75] proposed a dynamic mechanism to detect global outliers. For evaluation, three case studies from social network data were used and the results of the proposed method were evaluated in terms of F-score, precision, and recall.…”

Section: Unclassified Techniquesmentioning

confidence: 99%

Cleaning Big Data Streams: A Systematic Literature Review

2023

View full text Add to dashboard Cite

In today’s big data era, cleaning big data streams has become a challenging task because of the different formats of big data and the massive amount of big data which is being generated. Many studies have proposed different techniques to overcome these challenges, such as cleaning big data in real time. This systematic literature review presents recently developed techniques that have been used for the cleaning process and for each data cleaning issue. Following the PRISMA framework, four databases are searched, namely IEEE Xplore, ACM Library, Scopus, and Science Direct, to select relevant studies. After selecting the relevant studies, we identify the techniques that have been utilized to clean big data streams and the evaluation methods that have been used to examine their efficiency. Also, we define the cleaning issues that may appear during the cleaning process, namely missing values, duplicated data, outliers, and irrelevant data. Based on our study, the future directions of cleaning big data streams are identified.

show abstract

“…CatchSync [13] detects fraud by analyzing node properties (e.g., degree, HITS score, edge betweenness). The work [2,22,38] detect fraud by analyzing fraudulent communities. GCNEXT [16] is a detection model using expanded balance theory and GCN.…”

Section: Introductionmentioning

confidence: 99%

DP-GCN: Node Classification Based on Both Connectivity and Topology Structure Convolutions for Risky Seller Detection

Chen¹,

Sun²

2021

Preprint

View full text Add to dashboard Cite

A payment network contains transactions between sellers and buyers. Detecting risky (or bad) sellers on such a payment network is crucial to payment service providers for risk management and legal compliance. In this research, we formulate this task as a node classification task. Specifically, we aim to predict a label for each seller in a payment network, by analysing its properties and/or interactions. Nodes residing in different parts of a payment network can have similar local topology structures. Such local topology structures reveal sellers' business roles, e.g., supplier, drop-shipper, or retailer. We note that many existing solutions for graph-based node classification only consider node connectivity but not the similarity between node's local topology structure. Motivated by business need, we present a dual-path graph convolution network, named DP-GCN, for node classification. DP-GCN considers both node connectivity and topology structure similarity. The proposed model consists of three main modules: (i) a C-GCN module to capture connectivity relationships between nodes, (ii) a T-GCN module to capture topology structure similarities between nodes, and (iii) a multi-head self-attention module to align both properties. We evaluate DP-GCN on seven benchmark datasets against diverse baselines. We also provide a case study of running DP-GCN on three large-scale payment networks from PayPal, one of the leading payment service providers. Experimental results demonstrate DP-GCN's effectiveness and practicability. RELATED WORKOur research is related to studies in four areas: node connectivity embedding, node topology structure embedding, graph neural network, and graph-based fraud detection.

show abstract

BRNADS: Big data real-time node anomaly detection in social networks

Cited by 9 publications

References 5 publications

RETRACTED: The prediction model of personality in social networks by using data mining deep learning algorithm and random walk model

RETRACTED: The prediction model of personality in social networks by using data mining deep learning algorithm and random walk model

Cleaning Big Data Streams: A Systematic Literature Review

DP-GCN: Node Classification Based on Both Connectivity and Topology Structure Convolutions for Risky Seller Detection

Contact Info

Product

Resources

About