The Use of Multiplayer Perceptron Method to Identify Sexual Harassment on Social Media X (Twitter)
DOI:
https://doi.org/10.38035/dijemss.v6i6.4903Keywords:
Digital Evidence, NIST, Multilayer Perceptron, X (Twitter)Abstract
The Multilayer Perceptron (MLP) method, as a type of artificial neural network, is used in this study to classify tweets containing sexual harassment elements. This research begins with data collection from social media platform X (Twitter), where tweets that are considered relevant to the topic of sexual harassment are collected for further analysis. This data collection process was carried out by observing the principles of research ethics and maintaining the confidentiality of user identity. Once the data was collected, a text pre-processing stage was performed to ensure that the data used was clean and ready to be processed by the model. This pre-processing includes several important steps such as cleansing, slangword, and stopword removal. The data that has gone through this stage is then weighted using the TF-IDF method, a technique that helps determine the importance of certain words in a set of tweets. The processed data is then analyzed using the MLP algorithm. MLP was chosen due to its superior ability to handle complex and non-linear data. This algorithm is able to detect patterns that indicate the presence of sexual harassment elements in tweets, by classifying based on certain patterns of words, phrases, or contexts that often appear in cases of sexual harassment on social media. This research also uses the NIST Framework to ensure that the entire process of collecting, processing, and analyzing data is carried out in accordance with applicable digital forensic standards. This is important to maintain the validity and legality of the research results, especially if these results are used to support official investigations by the authorities. With the implementation of the MLP method, it is hoped that social media platforms and authorities can be more effective in detecting, preventing, and overcoming cases of sexual harassment in cyberspace
References
Mutia, A. (2023, July). Number of Twitter users in Indonesia ranked 4th in the world as of July 2023. Databoks. https://databoks.katadata.co.id/datapublish/2023/11/01/jumlah-pengguna-twitter-indonesia-duduki-peringkat-ke-4-dunia-per-juli-2023.
Bokolo, B. G., & Liu, Q. (2024). Artificial intelligence in social media forensics: A comprehensive survey and analysis. Electronics, 13(9). https://doi.org/10.3390/electronics13091671.
Budiman, K., Zaatsiyah, N., Niswah, U., Muhanna, F., & Faizi, N. (2020). Analysis of sexual harassment tweet sentiment on Twitter in Indonesia using Naïve Bayes method through National Institute of Standard and Technology digital forensic acquisition approach. Journal of Advanced Information Systems and Technology, 2(2), 21–30. https://journal.unnes.ac.id/sju/index.php/jaist.
Faizal, A., & Luthfi, A. (2024). Comparison study of NIST SP 800-86 and ISO/IEC 27037 standards as a framework for digital forensic evidence analysis. Journal of Information Systems and Informatics, 6(2), 701–718. https://doi.org/10.51519/journalisi.v6i2.717.
Daga, I., Gupta, A., Vardhan, R., & Mukherjee, P. (2020). Prediction of likes and retweets using text information retrieval. Procedia Computer Science, 168, 123–128. https://doi.org/10.1016/j.procs.2020.02.273.
Prasetya Wibawa, A., Lestar, W., Bella Putra Utama, A., Tri Saputra, I., & Nabila Izdihar, Z. (2020). Multilayer Perceptron untuk prediksi sessions pada sebuah website journal elektronik. Indonesian Journal of Data Science, 1(3), 57–67. https://doi.org/10.33096/ijodas.v1i3.15.
Sintia, Defit, S., & Nurcahyo, G. W. (2021). Product codefication accuracy with cosine similarity and weighted term frequency and inverse document frequency (TF-IDF). Journal of Applied Engineering and Technological Science, 2(2), 14–21. https://doi.org/10.37385/jaets.v2i2.210.
Umar, R., Riadi, I., & Zamroni, G. M. (2018). Mobile forensic tools evaluation for digital crime investigation. International Journal of Advanced Science, Engineering and Information Technology, 8(3), 949–955. https://doi.org/10.18517/ijaseit.8.3.3591.
Nur Faiz, M., Adi Prabowo, W., & Fajar Sidiq, M. (2018). Studi komparasi investigasi digital forensik pada tindak kriminal. Journal of Informatics, Information System, Software Engineering and Applications, 1(1), 63–70. https://doi.org/10.20895/INISTA.V1I1.
Bintang, R. A., Umar, R., & Yudhana, A. (2020). Analisis media sosial Facebook Lite dengan tools forensik menggunakan metode NIST. Techno (Jurnal Fakultas Teknik Universitas Muhammadiyah Purwokerto), 21(2), 125. https://doi.org/10.30595/techno.v21i2.8494.
Ngejane, C. H., Eloff, J. H. P., Sefara, T. J., & Marivate, V. N. (2021). Digital forensics supported by machine learning for the detection of online sexual predatory chats. Forensic Science International: Digital Investigation, 36, 301109. https://doi.org/10.1016/j.fsidi.2021.301109.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Farhan Wildan Giffary, Yudi Prayudi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish their manuscripts in this journal agree to the following conditions:
- The copyright on each article belongs to the author(s).
- The author acknowledges that the Dinasti International Journal of Education Management and Social Science (DIJEMSS) has the right to be the first to publish with a Creative Commons Attribution 4.0 International license (Attribution 4.0 International (CC BY 4.0).
- Authors can submit articles separately, arrange for the non-exclusive distribution of manuscripts that have been published in this journal into other versions (e.g., sent to the author's institutional repository, publication into books, etc.), by acknowledging that the manuscript has been published for the first time in the Dinasti International Journal of Education Management and Social Science (DIJEMSS).
