Spam detection on Twitter using a support vector machine and users’ features by identifying their interactions

Ahmad, Saleh Beyt Sheikh; Rafie, Mahnaz; Ghorabie, Seyed Mojtaba

doi:10.1007/s11042-020-10405-7

Cited by 24 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kai-Cheng et al [8] extracted two types of features, including raw data like follower count and derived features like follower growth rate and the length of the screen name. Saleh et al [9] summarized a bunch of features according to account information like age, length of the name, and count of followers and then used a support vector machine to separate bots from genuine users. Hrushikesh et al [10] ensemble the prediction results of three machine learning models to improve the classifying accuracy after a comprehensive account features collection, e.g., location, profile image, and daily average tweet count, and so on.…”

Section: Bot Detection Approachesmentioning

confidence: 99%

Botshape: A Novel Social Bots Detection Approach via Behavioral Patterns

Wu¹,

Ye²,

Mou³

2023

Advanced Information Technologies and Applications

View full text Add to dashboard Cite

An essential topic in online social network security is how to accurately detect bot accounts and relieve their harmful impacts (e.g., misinformation, rumor, and spam) on genuine users. Based on a real-world data set, we construct behavioral sequences from raw event logs. After extracting critical characteristics from behavioral time series, we observe differences between bots and genuine users and similar patterns among bot accounts. We present a novel social bot detection system BOTSHAPE, to automatically catch behavioral sequences and characteristics as features for classifiers to detect bots. We evaluate the detection performance of our system in ground-truth instances, showing an average accuracy of 98.52% and an average f1-score of 96.65% on various types of classifiers. After comparing it with other research, we conclude that BOTSHAPE is a novel approach to profiling an account, which could improve performance for most methods by providing significant behavioral features

show abstract

Section: Bot Detection Approachesmentioning

confidence: 99%