Current automated content moderation systems fail to protect children from harmful YouTube content, particularly in under-resourced, code-switched settings. These systems are often text-only, English-centric, and operate as ’black boxes,’ lacking the multimodal understanding and transparency needed for effective moderation. This thesis proposes a novel hybrid framework for the explainable multimodal detection of harmful content in videos with code-switching. The proposed framework integrates a fine-tuned classifier for accurate, scalable detection with an LLM-powered module that synthesizes the classifier’s internal evidential signals (e.g., text attention and visual heat maps) to generate faithful, human-readable rationales for each decision. As a primary case study, the framework will be developed and validated on an English–Filipino code-switched dataset. Expected contributions include a new dataset publicly available under controlled access (de-identified transcripts, blacked-out frames, extracted feature representations, and metadata via data-sharing agreement) and a blueprint for building more equitable, transparent, and trustworthy AI safety systems.

Grasping morality is vital in AI systems, particularly as they become more prevalent in human-focused applications. Yet, research is scarce on this topic. This study presents the Emotion-based Morality in Tagalog and English Scenarios (EMoTES-3K), a collection that shows commonsense morality in both Filipino and English. This dataset is instrumental for analyzing moral decisions in various situations and their justifications. Our tests show that EMoTES-3K is effective for moral text categorization, with the fine-tuned RoBERTa model scoring 94.95% accuracy in English and 88.53% in Filipino. The dataset also excels in text generation tasks, as shown by fine-tuning the FLAN-T5 model to produce clear moral explanations. However, the model faces challenges when dealing with actions that have mixed moral implications. This work not only bridges the gap in moral reasoning datasets for languages like Filipino but also sets the stage for future research in commonsense moral reasoning in artificial intelligence.