Detection of Topics from Video Transcripts by ML/DL Techniques

In the digital era, managing vast quantities of uncategorised text-based documents poses a significant challenge for institutions, as experienced by the Universidad Politecnica de Valencia (UPV) with their internal educational video system. Due to the lack of proper categorisation, the issue is represented by the difficulty students face in finding relevant content and the teachers keeping it updated. The paper aims to propose various Machine Learning and Deep Learning techniques aimed at assigning meaningful topics to these transcriptions, similar to how Wikipedia uses succinct, context-rich labels for its articles. This approach streamlines content access, enhances internal tracking and adds significant value to the institutions by improving data management and user experience.