Efficiently Detecting Web Spambots in a Temporally Annotated Sequence

Exploring a Self-Replication Algorithm to Flexibly Match Patterns

“…Spambots, also known as spam robots, are automated scripts or software applications designed to create and propagate unsolicited and potentially harmful content, including unwanted advertisements, phishing schemes, and malware [69]. According to [70], there are four types of spam detection techniques: content-based, link-based, machine learning, and string pattern matching-based. Subsequently, we compare Matcher Cells with techniques based on string pattern matching in the domain of spambot detection.…”

“…Alamro et al [70] propose an algorithm that can detect one or more sequences of indeterminate actions in text T in linear time. The algorithm takes into account temporal information, because it considers time-annotated sequences and requires a match to occur within a time window t. Authors state that VOLUME 11, 2023 some spambots might attempt to disguise their actions by varying certain actions.…”

“…In reference to the research conducted by Alamro et al [70], Matcher Cells exhibits comparable functionality by amalgamating multiple rules to identify variations in actions. Employing the One Match at a Time and Match per Time Frame semantic rules, Matcher Cells seamlessly incorporates temporal information, enabling it to effectively detect spambots that disguise their actions.…”