While quantitative data can be assessed rather easily using statistics, the automated evaluation of free texts poses a challenge, as the same set of fact can be described by totally different words and minimal deviations can result in contradictory meanings.
This is where text mining comes in. The term describes the assessment of high quality information from free texts, which uses various algorithm-based methods of analysis to identify and further process the texts’ contents.
The most common sources of information in this context are the internet as well as unstructured CRM-data and extensive collections of text, reports etc..
Text mining is used to automatically analyse a wide range of free texts, which can be categorised by means of their contents. Furthermore similar texts can be identified and sorted into groups using cluster-analyses. Existing information can be interlinked and it is possible to search for specific contents without knowing its precise wording. The list of applications could be extended endlessly.
It is crucial to define clear leading questions and suitable sources of data, which are then used to extract relevant information via text mining.
Emergent Actio carries out text mining projects for you and advises you regarding their implementation in your applications.