Show simple item record

dc.contributor.authorFortunatus, Meisy
dc.date.accessioned2019-10-29T23:29:34Z
dc.date.available2019-10-29T23:29:34Z
dc.date.issued2019
dc.identifier.urihttps://hdl.handle.net/10182/11038
dc.description.abstractCyber aggression is one of the most prevalent issues stemmed from the growing number of internet users. Given the numerous amount of online posts every day, it is not feasible to detect textual cyber aggression manually. This research focuses on analysing social media posts to find elements of cyber aggression and then build an algorithm that uses these elements in a set of rules to detect cyberbullying effectively. Lexicon enhanced rule-based method is used to detect cyber aggression on three different types of social media textual communication: single post from Facebook, question and answer pair from Formspring.me, and thread style from MySpace.com. The algorithm is evaluated using a combination of accuracy, precision, recall, and F1 measure. It was found that the algorithm performed best for single style data and the least for thread style data.en
dc.language.isoenen
dc.publisherLincoln Universityen
dc.rights.urihttps://researcharchive.lincoln.ac.nz/page/rights
dc.subjectcyber aggressionen
dc.subjecttextual aggressionen
dc.subjectharrassmenten
dc.subjectemoticon sentimenten
dc.subjectlexiconen
dc.subjectsocial mediaen
dc.subjectaggression detectionen
dc.subjectcyberen
dc.subjectbullyingen
dc.subjectcyber aggressionen
dc.subjectsentiment analysisen
dc.titleClassifying cyber aggression in social media postsen
dc.typeThesisen
thesis.degree.grantorLincoln Universityen
thesis.degree.levelMastersen
thesis.degree.nameMaster of Applied Scienceen
lu.thesis.supervisorAnthony, Patricia
lu.thesis.supervisorCharters, Stuart
lu.contributor.unitDepartment of Informatics and Enabling Technologiesen
dc.subject.anzsrc080107 Natural Language Processingen
dc.subject.anzsrc080709 Social and Community Informaticsen
dc.subject.anzsrc080309 Software Engineeringen


Files in this item

Default Thumbnail

This item appears in the following Collection(s)

Show simple item record