Skip to content
Research Article Open access CC BY 4.0

Ensemble Learning Based Prediction for Cyber Harassment Observations on Tweets

N. Sreevidya, Ashwini Hamsini, Rasala Vainateya, Chetla Arjun Naidu

Asian Journal of Research in Computer Science · pp. 102–113 · Published 18 Apr 2024

10.9734/ajrcos/2024/v17i6460

Abstract

Now a days social media plays crucial role in allowing individuals to express their views. Based on their views find the information of different keywords/statements like sadness, happiness, teasing, harassment and abuse. Online abuse, a novel form of pestering, have become increasingly predominant in online groups in modern civilization. Detecting harassment is indeed a significant challenge. Several studies provide information on cyber harassment, but none of them offer a solid remedy. Several studies provide information on cyber harassment, but none of them offer a solid remedy. Due to this reason, multiple models can be practiced to recognize and block harassment-related communications. We have utilized ensemble machine learning models to predict accurate results. The twitter dataset used for our research. We observe two models getting accuracy for RF+DT is 92% and SVM+LR is 93%. It is similar accuracy in individual models. So, there is no difference between Ensemble or individual model accuracy rate.

Ensemble machine learning prediction cyber harassment tweets

Cited by 1

1 citation reported by external sources — individual citing-article records aren't available to list yet.

Article metrics

Real usage data collected on this platform.

19

Page views

0

PDF downloads

2

Outbound clicks

1

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.