Visual Analysis of Implicit Social Networks for Suspicious Behavior Detection

Online social networks produce a visuality that reflects the attention economy governing this space. What is seen becomes elevated into prominence by networked publics that ‘perform’ affective expressions within platform affordances. We mapped Twitter images of refugees in two language spaces – English and Arabic. Using automated analysis and qualitative visual analysis, we found similar images circulating both spaces. However, photographs generating higher retweet counts were distinct. This highlights the impact of affective affordances of Twitter – in this case retweeting – on regimes of visibility in disparate spheres. Representations of refugees in the English language space were characterized by personalized, positive imagery, emphasizing solidarity for refugees contributing to their host country or stipulating innocence. Resonating images in the Arabic space were less personalized and depicted a more localized visuality of life in refugee camps, with an emphasis on living conditions in refugee camps and the efforts of aid organizations.

Download Full-text

Multidimensional Projections for Visual Analysis of Social Networks

Journal of Computer Science and Technology ◽

10.1007/s11390-012-1265-5 ◽

2012 ◽

Vol 27 (4) ◽

pp. 791-810 ◽

Cited By ~ 9

Author(s):

Rafael Messias Martins ◽

Gabriel Faria Andery ◽

Henry Heberle ◽

Fernando Vieira Paulovich ◽

Alneu de Andrade Lopes ◽

...

Keyword(s):

Social Networks ◽

Visual Analysis ◽

Analysis Of Social Networks

Download Full-text

Fights Behavior Detection Based on Space-Time Interest Points

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.577.659 ◽

2014 ◽

Vol 577 ◽

pp. 659-663

Author(s):

Jing Hu ◽

Xiang Qi ◽

Jian Feng Chen

Keyword(s):

Action Recognition ◽

Visual Analysis ◽

Detection Method ◽

Human Action Recognition ◽

Human Action ◽

Space Time ◽

Interest Points ◽

Behavior Detection ◽

Motion Energy ◽

Temporal Features

Human action recognition belongs to the senior visual analysis of computer vision, which involves image processing, artificial intelligence, pattern recognition and so on, is becoming one of the most hot research topic in recent years. In this paper, on the basis of comparative analysis and study towards current methods related to human action recognition, we propose a novel fights behavior detection method which is based on spatial-temporal interest point. Since most information of human action in video are indicated by the space-time interest points of video, we combine spatial-temporal features with motion energy image to describe information of video, and local spatial-temporal features are applied to extract fights behavior model by bags of words. Experimental results show that this method can achieve high accuracy and certain practical value.

Download Full-text

A novel spam detection technique for detecting and classifying the malicious profiles in online social networks

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-202937 ◽

2021 ◽

pp. 1-15

Author(s):

V.M. Priyadharshini ◽

A. Valarmathi

Keyword(s):

Social Networks ◽

Online Social Networks ◽

Support Vector Machine Classifier ◽

User Behavior ◽

Computation Time ◽

Detection Technique ◽

Support Vector ◽

Spam Detection ◽

Behavior Detection ◽

Novel Technique

Online social networks (OSNs) are utilized by millions of people from the entire world to communicate with others through Facebook and Twitter. The removal of fake accounts will increase the efficiency of the protection in OSNs. The construction of the OSN model has the nodes and the links to identify the fake profiles on Twitter. This paper proposes a novel technique to detect spam profiles and the proposed classifier is to classify the profile images from the dataset. The malicious profile detection technique is used to identify the fake profiles with the concept of a Twitter crawler that implements the extraction of data from the profile. The feature set analysis has been implemented with the feature related analysis. The user behavior detection utilizes the adjacent matrix to measure the similarity values within the friend’s profiles. The multi-variant Support Vector Machine classifier is developed for efficient classification with the kernel function. The proposed technique is compared with the well-known techniques of ECRModel, ISMA and DeepLink that the detection rate is 2.5% higher than the related techniques, the computation time is 220 s lesser than the related techniques and the proposed technique has 3.1% higher accuracy.

Download Full-text