Findings and Conclusion

Example of a pre and post process tagging visualization of a recording, with the post process being dramatically more dense — Pre and Post Process Tagging Visualization

It’s an important note that this process is not intended to replace human transcribers, instead this aims to enhance the role of human transcribers by shifting the focus from manual tagging to copy editing, thereby reducing repetitive tasks. Student workers are encouraged to modify tag names, adjust associated words, and create new categories based on trends identified in the primary tag sheet. This approach not only diversifies the tasks of student workers beyond transcription, which are often monotonous, with little to highlight on a CV, and enables them to engage in coding and instantly see the impact of their modifications.

Other advantages include:

All tags use a controlled vocabulary.
Tagging is more accurate, detailed, and relevant, helping researchers quickly identify thematic connections.
Tagging establishes a knowledge framework relevant to the collection that transcribers might lack in historical, scientific, or regional contexts key to the recordings.

My hope is that utilizing machine learning, Python, and JavaScript approaches will make digitizing these resources more efficient and accessible, ultimately promoting their preservation and availability to the public.