Benefits of automatic content classification
Taxonomies are used to classify content in an organized way to make it easy to navigate and find for other users, much the way a library catalogue works.
However, recent research has shown that up to two thirds of organizations cannot access their information assets due to poor information classification or tagging.
So if everyone agrees that proper content classification helps you find the information you need, the question that businesses must ask themselves is HOW to classify the masses of content they face every day?
There are many ways of doing this. In the past, this has often been a manual task, whereby users themselves placed content in different topics, folders, tags according to how they interpreted the content.
I am sure you have all had experience with shared network drives, directories in Windows File Manager, e-mail folders, intranet portals, etc..
Manual classification can work, but only if content is limited, focused and classification is done by true experts (not only of the taxonomy and the content itself, but also of user needs).
However, manual classification is a costly process that requires a lot of effort in order to be accurate and timely.
Automatic classification is often a far better alternative. There are many different technical solutions to automating, but even simple search-rule based classification will take you very far.
The benefits of automatic content classification are:
- More consistent. They produce the same unbiased results over and over. Might not always be 100% accurate or relevant, but if something goes wrong, it is at least it is easy to understand why.
- Larger context. Enforces classification the whole organizations perspective, not the individuals. For example, a person interested in sports might tag an article mentioning the player “Cristiano Ronaldo” in the “Football” sportstopic (correctly), but forget/not consider that it might be relevant also in the team topic “Real Madrid” and also in the country topic “Portuguese players” (whohc might be where others would look for the same article.
- Persistent. A person can only handle a certain number of incoming articles per day, whilst a classification engine works round the clock.
- Cost effective. Possible to handle thousands of articles much faster than a person.
To conclude, automate your content classification and consider using manual labor mainly for quality checking and approval of content.
Comintelli are in the process of writing a white paper that discusses content classification and are interested in any input you may have to this discussion, please join us!
By: Jesper Martell