Towards Curbing Cyber-Bullying in Malaysia by Author Identification of Iban and Kadazandusun Osn Text Using Deep Learning

Abstract

Online Social Network (OSN) is frequently used to carry out cyber-criminal actions such as cyberbullying. As a developing country in Asia that keeps abreast of ICT advancement, Malaysia is no exception when it comes to cyberbullying. Author Identification (AI) task plays a vital role in social media forensic investigation (SMF) to unveil the genuine identity of the offender by analysing the text written in OSN by the candidate culprits. Several challenges in AI dealing with OSN text, including limited text length and informal language full of internet jargon and grammatical errors that further impact AI's performance in SMF. The traditional AI system that analyses long text documents seems inadequate to analyse short OSN text's writing style. N-gram features are proven to efficiently represent the authors' writing style for shot text. However, representing N-grams in traditional representation like Tf-IDF resulted in sparse and difficult in grasping the semantic information from text. Besides, most AI works have been done in English but receive less attention in indigenous languages. In West Malaysia, the supreme languages that transcend ethnic boundaries are Iban of Sarawak and KadazanDusun of Sabah, which both are inherently under-resourced. This paper presented a proposed workflow of AI for short OSN text using two Under-Resourced Language (U-RL), Iban and KadazanDusun tweets, to curb the cyberbullying issue in Malaysia. This paper compares Tf-Idf (sparse) and SoA embedding-based (dense) feature representations to observe which representations best represent the stylistic features of the authors’ writing. N-grams of word, character, and POS were extracted as the features. The representation models were learned by different classifiers using machine learning (Naïve Bayes, Random Forest, and SVM). The convolutional neural network (CNN), a SoA deep learning model in sentence classification, was tested against the traditional classifiers. The result was observed by combining different representation models and classifiers on three datasets (English, Iban, and KadazanDusun). The best result was achieved when CNN learned embedding-based models with a combination of all features. KadazanDusun achieved the highest accuracy with 95.76%, English with 95.02%, and Iban with 94%..

A Systematic Literature Review on Social Media Slang Analytics in Contemporary Discourse

“…It is also portrayed as a multi-dimensional construct rooted in schema theory and communication style literature, emphasizing its multidimensional nature in the study of online language [35]. Short forms like "LOL," "btw," and "g2g" are identified as elements of Internet slang, reflecting the role of abbreviation and acronyms in digital communication [36]. Characterizing Internet slang as a new language with innovative and novel characteristics, it is considered as a form of creative advertising, highlighting its commercial and creative potential in digital spaces [14].…”

“…Such research is valuable for marketers and communication strategists seeking to optimize their advertising campaigns. [36] Cyberbullying Prevention and Online Identity…”

“…The utilization of such terminology provides a window into contemporary digital slang and language trends. A multifaceted data collection approach, involving the compilation of 50 recent tweets featuring profane phrases from a designated feed list is employed in [36]. Additionally, the extraction of tweets from ten prolific users for Iban and Kadazand.…”

“…Slang analytics is implemented within the field of marketing [35] in understanding how slang terms impact marketing campaigns, consumer engagement, or brand perception. In the context of cyberbullying [36] [40], slang analytics is applied to detect and address instances of cyberbullying to identify potentially harmful content. Slang analytics is observed in the domain of advertising [14] which could be used to assess how slang is used in advertisements, whether it resonates with the target audience, or if it has unintended consequences.…”

“…Within the marketing sector, [35] focuses on understanding the impact of slang terms on marketing has the challenge of quantifying slang's influence on consumer behavior. In the context of cyberbullying [36] and [40], slang analytics demands precise algorithms for detecting harmful intent within slang expressions. Slang analytics in advertising [14], requires the need for a nuanced understanding of slang in marketing with the target audience while avoiding unintended consequences.…”