Cloud Hosting

WHEN he was still schooling, Richard Wijaya (pic) witnessed firsthand the impact of cyberbullying on his classmates.

What seared into his memory was the helplessness of the victims in the face of the attacks due to the online anonymity of the perpetrators, he shared.

That experience inspired the 22-year-old to look for a solution when he wrote his final year paper before graduating with a Bachelor of Science (Hons) in Computer Science with a specialism in Data Analytics from Asia Pacific University of Technology & Innovation (APU).

Titled Expose Cyberbullying Tweets Using Machine Learning: A Data Science Approach, his paper has won a bronze award at the Young Inventors Journal Paper Writing Competition 2021.

Organised by the Association of Science, Technology and Innovation (ASTI), the competition challenged participants to look at social well-being and mental health issues, and think of a viable solution.

Richard, whose paper will be published in the Young Inventors Online Journal soon, beat 46 full paper writers from the Philippines, Thailand and Singapore when the results were announced on Feb 10.

In finding the best approach to identify potential cyberbullies and reduce cyberbullying, Richard, who hails from Jakarta, Indonesia, leveraged his data analytics knowledge by comparing several machine learning and deep learning algorithms, namely, Nave Bayes, Support Vector Machine (SVM) and Long Short-Term Memory (LSTM).

One of the applications of data analytics is called text processing. Sentences can be preprocessed into a form eligible to train the machine learning algorithms and produce a cyberbully detection model, he explained in a press release.

The outcome of his research, he said, could help the relevant authorities to detect cyberbullying content and apply necessary actions such as warning the possible perpetrators.

The end product of this research will not simply be a predictive model, but will evaluate the performance of the predictive model using suitable evaluation measures, he added.

Having gained recognition for his work, Richard said a detailed understanding of a topic needs to be achieved to deliver outstanding performance.

Fundamentally, a deep interest in the domain chosen is important if someone is intrigued to do a certain topic. This will help to dig up critical information to write a better paper.

He also expressed his gratitude to his project supervisor Mafas Raheem from the School of Computing at APU, who encouraged him to submit his paper for the competition.

He helped me a lot, from brainstorming to constructing the paper. He also helped me find a solution if I had any doubt, said Richard, adding that the preparation for the competition took about three weeks.

I needed to prepare a proposal and a journal paper. There were some hurdles along the way as I had to restructure the paper to ensure its legibility with important details in it, he shared.

Currently pursuing a masters degree in big data analytics in Birmingham in the United Kingdom, Richard aspires to elevate his professional knowledge of data analytics, and to be able to generate more innovative ideas that could help to build better societies globally.

Commenting on Richards win, Mafas said: With the right operationalisation of his machine learning predictive model, Richards studies in this domain will support the authorities in performing early detection of cyberbullying attempts, thus contributing to social well-being and mental health.

Read the original post:

Exposing cyberbullies with data analytics - The Star Online