“Isn’t it about time that we, as a profession, sell our abilities as well as the DAM system vendors sell their systems? After all, we’ve been proven vastly superior, despite the claims to the contrary. Human beings can make the connections between content and context that automated systems are incapable of making. While there have been improvements in face recognition, speech-to-text and other automated indexing methods, nothing beats a professional indexing team for improving accuracy and adding value to machine-generated metadata. For accuracy of retrieval, there is no replacement for a well-tailored controlled vocabulary used in combination with a well-designed indexing policy. This is one of the many places where information professionals excel..” [Read More]
Margie’s points resonate with my own view of automated metadata. I do think there is some value in these systems as ‘decision support’ tools where they can prompt asset cataloguers (of all levels of experience) with possible areas they have not considered. However, basing your ROI calculations on the assumption that a DAM system can carry out this task for you would be reckless.
In the past, we have featured a number of automated classification technologies that try to extract meaning from unstructured data like narrative copy and while some have produced some interesting results, without question the quality is below what could be used for anything other than the most basic of media repositories. As research initiatives they are interesting and probably legitimate for academic study but still questionable for commercial use.
In most of the example uses, the ROI proposition is where the cost of cataloguing is too great relative to the value obtained from the assets. For most Digital Asset Management uses cases such as preservation, media catalogues, training or corporate marketing, where re-use is crucial to ROI calculations, organisations run the risk of de-valuing their assets and cancelling out the benefits obtained when end-users simply cannot find anything that meets their needs.
- Metadata Automation Webinar Recording From New Jersey DAM Meetup Group
- Can Enterprise Taxonomy Management Survive Analyst Reticence - And Does Anyone Else Care Anyway?
- The Role Of Taxonomy Governance In DAM Interoperability Initiatives
- Google's Visual Case Study Of The Perils And Politics Of Automated Metadata
- The Perils And Politics Of Automated Metadata Generation