Scalable Learning Framework for Detecting New Types of Twitter Spam with Misuse and Anomaly Detection
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study introduces a new framework to detect novel Twitter spam by identifying anomalous tweets. It improves upon existing methods by first identifying known spam, then modeling normal tweets for better detection and fewer false positives.
Area Of Science
- Computer Science
- Social Media Analysis
- Cybersecurity
Background
- Social media platforms face increasing spam proliferation.
- Existing spam detection systems struggle against novel spam types.
- Developing effective countermeasures is crucial for platform integrity.
Purpose Of The Study
- To propose an anomaly detection-based framework for identifying new Twitter spam.
- To enhance spam detection rates and reduce false positives.
- To create an adaptable framework for evolving spam tactics.
Main Methods
- Modeling characteristics of non-spam tweets to identify deviations.
- Pre-detecting known spam using a decision tree.
- Employing one-class support vector machine and autoencoder for anomaly detection.
- Adjusting detection error costs for adaptability.
Main Results
- The proposed framework shows superior detection rates for unknown spam compared to conventional methods.
- Maintains equivalent or improved detection and false positive rates for known spam.
- Demonstrates adaptability to changing spam conditions.
Conclusions
- Anomaly detection, when combined with pre-detection of known spam, effectively identifies novel spam on Twitter.
- The framework offers a robust and adaptable solution for combating evolving spam threats.
- This approach balances detection accuracy with manageable false positive rates.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
Predicting Outbreaks
Predictive analytics, a branch of statistics, uses historical data, algorithmic models, and...
The Statistical Package for the Social Sciences, or SPSS, is a data management and analysis software suite. Developed by SPSS Inc. in 1968 and acquired by IBM in 2009, this tool was initially designed for social science data analysis, evolving to serve a wider range of disciplines. It was later renamed to Statistical Product and Service Solutions.
SPSS streamlines the process from data preparation to analysis and reporting. It is characterized by its user-friendly interface, which conceals...