<span>This paper presents the task of Author Identification for KadazanDusun language by using tweets as the source of data to perform Author Identification task of short text on KadazanDusun, which is considered as one the under-resourced language in Malaysia. The aim of this paper is to demonstrate Author Identification of short text on KadazanDusun. Besides, this paper also examines the performance of two machine learning algorithms on the KadazanDusun data set by analyzing the stylometric features. Stylometric features are used to quantify the writing styles of the authors which includes character n-grams and word n-grams. The workflow of Author Identification implements the machine learning approach to solve the single-labelled multi-class problem and predict the author of a given message in KadazanDusun. Two classifiers are used to compare the accuracy including Naïve Bayes and Support Vector Machine (SVM). The results show that the combination of n-grams which is word-level unigram and {1-5}-grams with character 3-grams are the most relevant stylometric features in identifying the author of KadazanDusun message with an accuracy of 80.17%. The results also show that SVM classifier has outperformed Naive Bayes in this Author Identification task with the accuracy of 80.17%.</span>
Nowadays, nearly all people utilize the device which is connected to Internet. People are accustomed to the use information technology devices in their daily life to interact with other people. Currently, many social media platforms such as Facebook, Twitter, Instagram, and YouTube are becoming popular. This study selected Twitter platforms, which is started to gain popularity. By the rapid growth of users signing up for Twitter accounts, at the same time, cybercrime started to bloom each year in social media platforms. Cyberbully is one of the cybercrime practices which had caused a significant impact on the targeted victims. The victims experienced social pressure, which they need to bear each day while the bullies stayed free behind the veil of anonymity. This study aims to identify the common vulgar words used by the cyberbullies on Twitter. Also, this study is subject to produce essential features of Twitter based on the collected tweets. The evaluation in this study includes the occurrences of the vulgar word perpetrated by the cyberbullies from Twitter. This study detected the usage of vulgar words in cyberbully activities on Twitter platform. A list of vulgar words were extracted and evaluated from a corpus of 50 Twitter users who posted a various number of tweets. The vulgar words detection in the tweets enable the tracking process of the cyberbully activities. In the evaluation section, we discussed how the usage of the vulgar words would define the user’s earnestness in doing the cyberbully activities in the Twitter. This study shows there are users with a low number of tweets have a high number of vulgar words occurrences, while other users with high numbers of tweets but less number of vulgar words occurrences. The information collected in this study is expected to assist marking users with a high number of vulgar words occurrences who tend to have high possibilities in doing cyber-bully activities.
This paper presents Author Identification (AI) task using different language which are English and Under-Resourced Languages (U-RL) (i.e. KadazanDusun and Iban). In this paper, the performance of AI task is analysed using English and the U-RL datasets in terms of accuracy. Different stylometric features and emerging machine learning algorithms (i.e. SVM and Random Forest) are examined to obtain optimal results in AI task. The approach used in AI task is based on supervised machine learning. Cross-validation is used to evaluate the performance of AI task. The findings include the performance comparison of different stylometric feature and classifiers between the three datasets based on their accuracy values. The combination of word n-grams with character 3-grams achieved the highest accuracy with almost 75% using English dataset. For classifier, SVM gained better result for all three datasets compared to Random Forest.
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%..
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.