IDENTIFYING ONLINE SEXUAL GROOMING CONTENT IN SOCIAL MEDIA USING CLASSIFICATION TECHNIQUE
Children nowadays are in danger more than ever. With the advent of technology, these kids are often the target of online sexual grooming activity. This threat is prevalent on social media, where innocent children are exposed to online predators. This paper uses a classification technique to identify online sexual grooming content in the form of text available on social media sites. This is because users are unaware of the contents lurking within any social media posts and comments, so a tool is needed to detect said grooming content to give awareness and censor it. The dataset used in the experiment is collected from different social media sites such as YouTube, Instagram, and Twitter. The inter-rater agreement is used to validate the process of manual data annotation. For the classification technique it is develop using neural networks algorithm based on n-gram and sequence features. In the end, the classification algorithm will be evaluated by comparing the detection rate between the algorithm and human perception. For the future works the developed detection model can be deployed for in a web-based system such as a browser extension. This can be as an approach for implementing awareness intervention sexual grooming conversation.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a copyright form (JACTA) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).