<![CDATA[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]]>
