scholarly journals Spammer Group Detection Using Machine Learning Technology for Observation of New Spammer Behavioral Features

2021 ◽  
Vol 29 (2) ◽  
pp. 61-76
Author(s):  
Li-Chen Cheng ◽  
Hsiao-Wei Hu ◽  
Chia-Chi Wu

Recently, the rapid growth in the number of customer reviews on e-commence platforms and in the amount of user-generated content has begun to have a profound impact on customer purchasing decisions. To counter the negative impact of social media marketing, some firms have begun hiring people to generate fake reviews which either promote their own products or damage their competitor's reputation. This study proposes a framework, which takes advantage of both supervised and unsupervised learning techniques, for the observation of behaviors among spammers. Then, based on the behavior of participants on web forums, the authors build up a post-reply network. The main focus is on the behavior-related features of the reviews, their propagation, and their popularity. The primary objective of this study is to build an effective online spammer detection model and the method detailed in this work can be used to improve the performance of spammer detection models. An experiment is carried out with a real dataset, the results of which indicate that these new features are important for identifying spammers. Finally, random walk clustering is applied to investigate the post-reply network. Some interesting and important features are observed in the interactions between a group of spammers which could be subjected to further research.

Author(s):  
Michael E. Whitman ◽  
Herbert J. Mattord

This chapter provides a case study of current practices and lessons learned in the provision of distance learning (DL)-based instruction in the field of information security. The primary objective of this case study was to identify implementations of distance learning techniques and technologies that were successful in supporting the unique requirements of an information security program that could be generalized to other programs and institutions. Thus the focus of this study was to provide an exemplar for institutions considering the implementation of distance learning technology to support information security education. The study found that the use of lecture recording technologies currently available can easily be used to record in-class lectures which can then be posted for student use. VPN technologies can also be used to support hands-on laboratory exercises. Limitations of this study focus on the lack of empirical evidence collected to substantiate the anecdotal findings.


Pharmaceutics ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 341
Author(s):  
Priusha Ravipati ◽  
Bice Conti ◽  
Enrica Chiesa ◽  
Karine Andrieux

Dermatillomania or skin picking disorder (SPD) is a chronic, recurrent, and treatment resistant neuropsychiatric disorder with an underestimated prevalence that has a concerning negative impact on an individual’s health and quality of life. The current treatment strategies focus on behavioral and pharmacological therapies that are not very effective. Thus, the primary objective of this review is to provide an introduction to SPD and discuss its current treatment strategies as well as to propose biomaterial-based physical barrier strategies as a supporting or alternative treatment. To this end, searches were conducted within the PubMed database and Google Scholar, and the results obtained were organized and presented as per the following categories: prevalence, etiology, consequences, diagnostic criteria, and treatment strategies. Furthermore, special attention was provided to alternative treatment strategies and biomaterial-based physical treatment strategies. A total of six products with the potential to be applied as physical barrier strategies in supporting SPD treatment were shortlisted and discussed. The results indicated that SPD is a complex, underestimated, and underemphasized neuropsychiatric disorder that needs heightened attention, especially with regard to its treatment and care. Moreover, the high synergistic potential of biomaterials and nanosystems in this area remains to be explored. Certain strategies that are already being utilized for wound healing can also be further exploited, particularly as far as the prevention of infections is concerned.


Electronics ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 692
Author(s):  
Wen-Chia Tsai ◽  
Jhih-Sheng Lai ◽  
Kuan-Chou Chen ◽  
Vinay M.Shivanna ◽  
Jiun-In Guo

This paper proposes a lightweight moving object prediction system to detect and recognize pedestrian crossings, vehicles cutting-in, and vehicles ahead applying emergency brakes based on a 3D Convolution network for behavior prediction. The proposed design significantly improves the performance of the conventional 3D convolution network (C3D) adapted to predict the behaviors employing behavior recognition network capable of performing object localization, which is pivotal in detecting the numerous moving objects’ behaviors, combining and verifying the detected objects with the results of the YOLO v3 detection model with that of the proposed C3D model. Since the proposed system is a lightweight CNN model requiring far lesser parameters, it can be efficiently realized on an embedded system for real-time applications. The proposed lightweight C3D model achieves 10 frames per second (FPS) on a NVIDIA Jetson AGX Xavier and yields over 92.8% accuracy in recognizing pedestrian crossing, over 94.3% accuracy in detecting vehicle cutting-in behavior, and over 95% accuracy for vehicles applying emergency brakes.


2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Tahani Daghistani ◽  
Huda AlGhamdi ◽  
Riyad Alshammari ◽  
Raed H. AlHazme

AbstractOutpatients who fail to attend their appointments have a negative impact on the healthcare outcome. Thus, healthcare organizations facing new opportunities, one of them is to improve the quality of healthcare. The main challenges is predictive analysis using techniques capable of handle the huge data generated. We propose a big data framework for identifying subject outpatients’ no-show via feature engineering and machine learning (MLlib) in the Spark platform. This study evaluates the performance of five machine learning techniques, using the (2,011,813‬) outpatients’ visits data. Conducting several experiments and using different validation methods, the Gradient Boosting (GB) performed best, resulting in an increase of accuracy and ROC to 79% and 81%, respectively. In addition, we showed that exploring and evaluating the performance of the machine learning models using various evaluation methods is critical as the accuracy of prediction can significantly differ. The aim of this paper is exploring factors that affect no-show rate and can be used to formulate predictions using big data machine learning techniques.


2020 ◽  
Vol 5 (15) ◽  
pp. 71-76
Author(s):  
Nurul Aien Abd Aziz ◽  
Noreen Noor Abd Aziz ◽  
Mohd Hafizan Musa ◽  
Shaherah Abdul Malik ◽  
Rusnani Mohamad Khalid ◽  
...  

In March 2020, the world was first hit by Covid-19 that started to have negative impact on all sectors including education. Most of the higher learning institutions had a shift to use the technology in imparting knowledge and conducting online learning for students. This paper analyzed the effect of attitude, interruption, personal skills and technology skills towards effective online learning. A total of 375 valid questionnaire responses was coded and analyzed using PLS-SEM analysis. The findings showed the attitude and technology skills were significant factors to the barriers of effective online learning among students. Keywords: Online Learning; Technology; Education learning; Technology skill eISSN: 2398-4287© 2020. The Authors. Published for AMER ABRA cE-Bs by e-International Publishing House, Ltd., UK. This is an open access article under the CC BYNC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Peer–review under responsibility of AMER (Association of Malaysian Environment-Behaviour Researchers), ABRA (Association of Behavioural Researchers on Asians) and cE-Bs (Centre for Environment-Behaviour Studies), Faculty of Architecture, Planning & Surveying, Universiti Teknologi MARA, Malaysia. DOI: https://doi.org/10.21834/ebpj.v5i15.2511.


2021 ◽  
Author(s):  
◽  
Sarah Bradbury

<p>Rationale: The profile of acquisition for MDMA self-administration differs from that of amphetamine and cocaine self-administration in that fewer rats meet an acquisition criterion and the latency to acquisition is longer. These characteristics of MDMA self-administration may be because it preferentially stimulates serotonin (5HT) release whereas self-administration has generally been attributed to enhanced dopamine (DA) neurotransmission. Because 5HTergic agonists are not self-administered and increased synaptic 5HT decreased self-administration of other drugs, MDMA self-administration may be initially inhibited by the pronounced 5HT response. Accordingly, the acquisition of MDMA self-administration might proceed as a result of deficits in 5HT neurotransmission and a corresponding disinhibition of DA neurotransmission.  Objective: The primary objective was to determine the role of 5HT in the acquisition and maintenance of MDMA self-administration.  Methods: MDMA-induced increases of extracellular 5HT and DA and their primary metabolites were measured in the DA terminal regions of the nucleus accumbens (NAc) using in vivo microdialysis, prior to the commencement of MDMA self-administration. The relationship between MDMA-induced increases of neurotransmitter levels and the acquisition of MDMA self-administration was assessed. A subsequent study depleted brain 5HT by administering the neurotoxin, 5,7 – DHT, or vehicle into the lateral ventricle of the left hemisphere, prior to the commencement of MDMA self-administration. The proportion of subjects that acquired MDMA self-administration and the latency to acquire MDMA self-administration was compared for the two groups. In order to determine effects of MDMA self-administration on 5HT and DA responses, behaviours that reflect 5HT and/or DA neurotransmission were measured 5 or 14 days after self-administration of 165 mg/kg MDMA, or 14 days after vehicle self-administration. These time periods were chosen because they reflect a period of 5HT deficits (5 days) and recovery (14 days). Finally, the effect of abstinence on MDMA self-administration was measured.  Results: The MDMA-induced increase of extracellular 5HT was significantly lower for the group that subsequently acquired MDMA self-administration but the MDMA-induced increase in DA was not different from the group that failed to acquire self-administration. 5, 7-DHT administration significantly decreased tissue levels of 5HT, but not DA. MDMA self-administration was facilitated by the lesion; 100% of the lesion group acquired MDMA self-administration, whereas only 50% of the control group acquired self-administration. Five days following the last MDMA self-administration session, DAergic behaviours were enhanced and 5HTergic behaviours were reduced relative to the control group. These differences in 5HTergic mediated behaviours were not apparent 14 days after self-administration but the DAergic behaviours remained elevated. The pattern of self-administration did not differ as a function of the length of the abstinence period.  Conclusions: The variability in acquisition of MDMA self-administration was related to the magnitude of the 5HT response evoked by initial exposure to MDMA. These findings suggested that predisposing differences in the 5HT response might explain differences in the variability in acquisition of MDMA self-administration. The negative impact of 5HT on the acquisition of MDMA self-administration was clearly demonstrated following a 5, 7-DHT lesion. Thus, 5HT limits the development of MDMA self-administration. With repeated exposure to self-administered MDMA, behavioural responses indicative of 5HT activation were reduced whereas behavioural indices of DA activation were increased. The maintenance of MDMA self-administration was comparable regardless of whether there was a forced abstinence period or not. These data are consistent with the hypotheses that 5HT is inhibitory to the acquisition, but not the maintenance, of MDMA self-administration. Rather, the maintenance of self-administration might reflect sensitised DA responses that became apparent following repeated exposure.</p>


Author(s):  
Elżbieta Zębek

The primary objective of the water protection in the Water Framework Directive No. 2000/60/ EC is to maintain and improve the water environment by achieving good water status. These provisions have been implemented into Polish legislation in the Water Law Act of 2017. These goals are achieved by the use of appropriate legal instruments as a system of water-law approvals, including a permit, notification and legal-water assessment. The subject of the analysis is water-legal assessments as a new legal and administrative instrument of water protection. The aim is to deter-mine the legal nature of water-law assessments and to indicate their role in the protection of surface waters. Obtaining this assessment is required for investments that may affect the possibility of achieving environmental goals. If the planned investment has a positive or no impact on the possibility of achieving the environmental goals, it seems that the legal-water assessment is made. In the case of a negative impact, the obligation to submit documents confirming that all measures are taken to mitigate the negative effects of the impact on the state of water bodies are imposed. In this way, the legislator strengthened the protection of waters by imposing the obligation to meet additional conditions for large-scale investments that have a negative impact on the water environment.


2021 ◽  
Vol 2 (1) ◽  
pp. 53-62
Author(s):  
Dea Putri Amanda ◽  
Nuri Aslami

The purpose of this study was to determine the effect of brand image or brand image and advertising on insurance policy purchasing decisions made by insurance consumers. The results of the study state that the first is the influence of brand image or brand image factors on the purchase choice of insurance policy customers. second, that there is no effect of advertising on the choice to purchase an insurance policy. third, that there is a positive influence between brand image and the negative impact of advertising on insurance policy purchasing decisions.


Author(s):  
Sonali Banerjee ◽  
Kaustuv Deb ◽  
Atanu Das ◽  
Rajib Bag

E-learning has a great impact on learners today. E-learning supports enhancing learner knowledge anytime, anywhere with lesser efforts than traditional models. In these situations, nonlinear approaches often modify teaching and learning strategies according to students' needs, and hence, automated machine-guided approaches seem useful in the name of adaptive learning. It identifies individual learner styles and provides the most suitable strategy that fits each learner as a case of personalization. Adaptive learning uses personalization for continuously improving student outcomes. Personalized learning takes place when e-learning systems use educational experience supporting desires, objectives, endowments, and curiosities of each individual learner. This work has reviewed the recent developments in the problem area of learning personalization through adaptive learning. Then the solution domain methods are compared to identify the knowledge and technology gap from their limitations. These analyses help to identify research potentials in learning technology for future works.


Sign in / Sign up

Export Citation Format

Share Document