Abstrakt
There are many kinds of data that libraries store. Every set of data originates from a different library activity.
Sometimes we need stored data for further use. Sometimes we do not and when we do not know what to do with it, we just store it.
Data just pile up with time. We spend manpower, capacity of servers and money to store it.
We store it although we do not know, if we really need everything. We just can not delete it.
Sometimes we use some of the data to do statistical reports. But what about the rest of it? Combination of methods of information technology can give us an answer.
Data mining is a process that allows us to do some powerful operations with our data. For example, we can discover what kind of user is the most frequent in our library, which is useful for creating a model.
We can also predict events, visualize data and detect potential abuse and so on. But if we want to apply data mining in our institution we have to be aware of many things.
We can not use every method for every kind of data. We should be aware of the limits of our data and at the same time we also have to be mindful of the limits of used methods.
We must know what we do have in our storage and also what we do not have. We should be aware of delicacy of some data and we should take steps to avoid misuse.
Even if we get good results from data, we have to know the right interpretation too. So how to use data mining in a library? Are there any advantages? This poster focuses on the usage of data mining with the data of University Library of Silesian University.
It will provide answers to following questions: What kind of data do we actually have? What can we do with them? What kind of methods are suitable for our data? And what do the results indicate?