ISSN (Online): 2455-3662 EPRA International Journal of Multidisciplinary Research (IJMR) - Peer Reviewed Journal Volume: 10| Issue: 1| January 2024|| Journal DOI: 10.36713/epra2013 || SJIF Impact Factor 2023: 8.224 || ISI Value: 1.188 2024 EPRA IJMR | http://eprajournals.com/ | Journal DOI URL: https://doi.org/10.36713/epra2013 --------------------------------------------------------------------14 AN AUTOMATIC HATE SPEECH DETECTION IN SOCIAL MEDIA THROUGH COMPUTATIONAL LINGUISTICS: INFIDELITY VIDEOS IN FOCUS Klein Mamayabay 1 , Danilo G. Baradillo 2 1 PhD, Teacher Education Programs, St. Mary’s College of Tagum, Inc., Tagum City, Philippines 2 PhD, Program Chair, University of the Immaculate Conception, Davao City, Philippines Article DOI: https://doi.org/10.36713/epra15377 DOI No: 10.36713/epra15377 ABSTRACT The escalating prevalence of hate speeches, amplified by the misguided use of social media, introduces alarming challenges to the safeguarding of human rights and individual welfare. Motivated by this, the study explored the detection and classification of hate speech, specifically as observed in speeches and comments related to infidelity videos on YouTube Channel of Raffy Tulfo in Action. Further, the study utilized a computational linguistic algorithm through Long Short-Term Memory (LSTM). Additionally, the study sought to understand the distinctions in linguistic features between hate speech and non-hateful speech through LSTM. The researcher used 9,600,586 tokens for the analysis. To answer the first research question, the employment of LSTM helped identify hate speeches from non-hate speeches through effective data gathering through YouTube Application Programming Interface (API) and Whisper AI, text processing, labeling, coding, and algorithm deployment. Through that process, LSTM also classified them per target, including sex, quality, physical attributes, disability, religion, race, and class. Further, to answer the second research question, the study was able to identify 35 lexicons. Some samples include peenoise, U10, kokey, taitok, quibolok, squami, and shut@, which were used negatively. Lastly, to answer the last question, tokenization, embedding, sequential dependencies, padding, training-testing, and evaluating helped LSTM assess hate speech linguistic features. It is evident in the confusion matrix showing 46% true positives and 49% true negatives and its evaluation performance of 95% F1 score, affirming its high robustness and reliability. KEYWORDS: Applied linguistics, language, hates speeches, infidelity cases, computational linguistics, Long Short Term- Memory (LSTM), Philippines INTRODUCTION Hate speech is a malicious expression that uses offensive language directed to a person or group of people based on the characteristics they are representing in areas including gender, relationships, politics, ethnicity, race, beliefs, etc. [1] and, sadly, it is now on the rise with the advent of social media [2], [3], [4], [5], [6]. In addition, the United Nations (UN) emphasized the dangers of hate speech to human rights and life [7], especially on the increasing cases of infidelity where studies found that people’s comments and reactions toward their partners’ cheating behavior could go up from verbal assaults to killing their unfaithful partner, thus, creating a very alarming human behavior [8] and [9]. In a study conducted in Germany, researchers found out that more than half of the participants indicated that they were more likely to commit cheating on their partners. Further, in the same country, another study found that 77.7% of the participants indicated that they had caught or suspected that their current or previous mates had been unfaithful, and during the data analysis, the results showed that some of their immediate comments and reactions about the issue were through violence, humiliating their partners, terminating their relationship in a harsh manner, using of psychological abuse, and hateful words and statements against their partners [10], [11]. Despite the relevance of this existing literature, there is only a little research utilizing computational linguistics to analyze and detect hate speech concerning cases of infidelity in the uploaded videos and comments on social media, particularly in the context of Philippines [12]. Additionally, with the advocacy of the United Nations in combatting hate speech, which can expose those targeted to discrimination, abuse, and violence, they heighten the necessity and priority in monitoring and analyzing hate speech through research. Motivated by these gaps, the researcher recognized the urgency to undertake this study in order to contribute to the prevention of any potential detrimental effects it may pose to our society [7] This study aims to generate hate-contained datasets for application developers to combat online hate speech. The results can be used by educators and students in discussions and assessments. Additionally, infographics will be created to raise awareness of hate speech prevalence on social media. The study’s algorithms will contribute to fostering an inclusive online community. Findings will be disseminated through