UGC Approved Journal no 63975(19)

ISSN: 2349-5162 | ESTD Year : 2014
Call for Paper
Volume 11 | Issue 3 | March 2024

JETIREXPLORE- Search Thousands of research papers



WhatsApp Contact
Click Here

Published in:

Volume 9 Issue 9
September-2022
eISSN: 2349-5162

UGC and ISSN approved 7.95 impact factor UGC Approved Journal no 63975

7.95 impact factor calculated by Google scholar

Unique Identifier

Published Paper ID:
JETIR2209107


Registration ID:
502205

Page Number

b44-b50

Share This Article


Jetir RMS

Title

ADOPT TO COMBAT MISINFORMATION ATTACKS IN OTHER REPUTATION SYSTEMS FOR RUMOUR DETECTION ON SOCIAL NETWORKS

Abstract

Online reviews provide customers with product evaluations to make decisions. Unfortunately, fake reviews ("spam") can be used to manipulate assessments by professional spammers, who have learned increasingly insidious and powerful spam tactics by adapting the detectors they deploy. Spam tactics are difficult to capture because they can change rapidly over time, vary between spammers and target products, and, crucially, remain unknown in most cases. Furthermore, most existing detectors focus on detection accuracy, which is inconsistent to maintain confidence in product evaluations. To address these challenges, we formulate a minimax game in which spammers and spam detectors compete on their actual goals, not just based on detection accuracy. The Nash equilibrium of the game leads to a stable detector that is not affected by any mixed detection strategy. However, the game has no closed-form solutions and cannot differentiate between typical gradient-based algorithms. We turn the game into two dependent Markov Decision Processes (MDPs) to allow efficient stochastic optimization based on multi-armed bandits and policy gradients. We conduct experiments on three large review datasets using various state-of-the-art spam and detection strategies and show that the optimization algorithm can reliably find a balanced detector that is robust and effective against the adoption of any mixed spam strategy of spammers to achieve their actual goals. Our code is available at https://github.com/YingtongDou/Nash-Detect.

Key Words

Spam detection, Nash-Detect, Accuracy, Minimax game, Markov Decision Process.

Cite This Article

"ADOPT TO COMBAT MISINFORMATION ATTACKS IN OTHER REPUTATION SYSTEMS FOR RUMOUR DETECTION ON SOCIAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 9, page no.b44-b50, September-2022, Available :http://www.jetir.org/papers/JETIR2209107.pdf

ISSN


2349-5162 | Impact Factor 7.95 Calculate by Google Scholar

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 7.95 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Cite This Article

"ADOPT TO COMBAT MISINFORMATION ATTACKS IN OTHER REPUTATION SYSTEMS FOR RUMOUR DETECTION ON SOCIAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 9, page no. ppb44-b50, September-2022, Available at : http://www.jetir.org/papers/JETIR2209107.pdf

Publication Details

Published Paper ID: JETIR2209107
Registration ID: 502205
Published In: Volume 9 | Issue 9 | Year September-2022
DOI (Digital Object Identifier):
Page No: b44-b50
Country: -, -, India .
Area: Engineering
ISSN Number: 2349-5162
Publisher: IJ Publication


Preview This Article


Downlaod

Click here for Article Preview

Download PDF

Downloads

000106

Print This Page

Current Call For Paper

Jetir RMS