scholarly journals Cost-based heterogeneous learning framework for real-time spam detection in social networks with expert decisions

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Jaeun Choi ◽  
Chunmi Jeon
Keyword(s):  
Social Networks ◽  
Real Time ◽  
Spam Detection ◽  
Learning Framework ◽  
Heterogeneous Learning

scholarly journals A Heterogeneous Ensemble Learning Framework for Spam Detection in Social Networks with Imbalanced Data

2020 ◽  
Vol 10 (3) ◽  
pp. 936 ◽  
Author(s):  
Chensu Zhao ◽  
Yang Xin ◽  
Xuefeng Li ◽  
Yixian Yang ◽  
Yuling Chen
Keyword(s):  
Social Networks ◽  
Ensemble Learning ◽  
Class Imbalance ◽  
Imbalanced Data ◽  
Machine Learning Algorithms ◽  
Spam Detection ◽  
Real World Data ◽  
Learning Framework ◽  
The Impact ◽  
Base Module

The popularity of social networks provides people with many conveniences, but their rapid growth has also attracted many attackers. In recent years, the malicious behavior of social network spammers has seriously threatened the information security of ordinary users. To reduce this threat, many researchers have mined the behavior characteristics of spammers and have obtained good results by applying machine learning algorithms to identify spammers in social networks. However, most of these studies overlook class imbalance situations that exist in real world data. In this paper, we propose a heterogeneous stacking-based ensemble learning framework to ameliorate the impact of class imbalance on spam detection in social networks. The proposed framework consists of two main components, a base module and a combining module. In the base module, we adopt six different base classifiers and utilize this classifier diversity to construct new ensemble input members. In the combination module, we introduce cost sensitive learning into deep neural network training. By setting different costs for misclassification and dynamically adjusting the weights of the prediction results of the base classifiers, we can integrate the input members and aggregate the classification results. The experimental results show that our framework effectively improves the spam detection rate on imbalanced datasets.

scholarly journals A Mapping Study to Investigate Spam Detection on Social Networks

2017 ◽  
Vol 11 (11) ◽  
pp. 16-34
Author(s):  
Balogun Abiodun Kamoru ◽  
Azmi Jaafar ◽  
Masrah Azrifah Azmi Murad
Keyword(s):  
Social Networks ◽  
Spam Detection ◽  
Mapping Study

scholarly journals The Clubhouse Phenomenon: Do We Need Another Social Network?

2021 ◽  
Author(s):  
Wadim Strielkowski
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Social Networking ◽  
Real Time ◽  
Group Psychotherapy ◽  
Text Messages ◽  
Online Video ◽  
Conference Call ◽  
Start Up ◽  
Further Development

Being a combination of the conference call, talkback radio, audio podcast, and an online video chat, Clubhouse is a new social networking app that gained over 10 million users and over $100 in valuation in just 8 months. Unlike other social networks, it offers a real-time streaming audio chat that does not ask users to share any unnecessary information like exchanging text messages, conducting video calls, or sharing photos. Instead, Clubhouse users can listen to real-time conversations, contribute to these conversations and create their own conversations for the others to listen and to interact with. Often nicknamed a “Silicon Valley’s hottest start-up”, Clubhouse positions itself as an “exclusive” and “alternative” social network that attracts various celebrities and people who just want to talk to each other. Launched in March 2020, amidst the COVID-19 pandemic with its social distancing and lockdowns, Clubhouse offered its users a space for the digital group psychotherapy where people could solve their problems by talking them through with strangers. However, it is unclear what is going to happen to this new social network in the post-pandemic world after all of its hype eventually evaporates. This paper discusses the possible underlying motives for the Clubhouse creation and its real purposes. Moreover, it looks at the three possible scenarios of its further development.

Detecting Pharmaceutical Spam in Microblog Messages

2011 ◽  
pp. 101-115
Author(s):  
Kathy J. Liszka ◽  
Chien-Chung Chan ◽  
Chandra Shekar
Keyword(s):  
Data Mining ◽  
Social Networks ◽  
Social Network ◽  
Online Social Networks ◽  
Cell Phones ◽  
Pharmaceutical Products ◽  
Spam Detection ◽  
Data Mining Techniques ◽  
Flow Through ◽  
Special Category

Microblogs are one of a growing group of social network tools. Twitter is, at present, one of the most popular forums for microblogging in online social networks, and the fastest growing. Fifty million messages flow through servers, computers, and cell phones on a wide variety of topics exchanged daily. With this considerable volume, Twitter is a natural and obvious target for spreading spam via the messages, called tweets. The challenge is how to determine if a tweet is a spam or not, and more specifically a special category advertising pharmaceutical products. The authors look at the essential characteristics of spam tweets and what makes microblogging spam unique from email or other types of spam. They review methods and tools currently available to identify general spam tweets. Finally, this work introduces a new methodology of applying text mining and data mining techniques to generate classifiers that can be used for pharmaceutical spam detection in the context of microblogging.

Sign in / Sign up

Export Citation Format

Share Document