Maritime Media Intelligence provides overall aspects of media content, which is of specific interest to them and subject to changing demand; what they provide may include documentation, content, analysis, specifically or widely.
Most of the content in the organization, more than 80%, consists of unstructured content, so different tools are needed for statistical data processing. Text mining discovers previously unknown information by the system, automatically extracting data from various sources. Text mining is different from what we know as web search. In web searches, users are usually looking for something already known and written by someone else. Text mining will provide results that have an indirect relationship and provide content search results.
Text mining is a study of NLP (Natural Language Processing) for discourse search and extraction based on objects and contents. The difference between data mining and text mining is that in text mining, patterns are extracted not from the database but the NLP (Natural Language Processing) process.
With the NLP approach, it will be possible to conduct discourse searches and automatically generate existing objects such as names of people, times, names of organizations, and names of places. In full, the capabilities of text mining are:
NER (Named Entity Recognition) - automatically recognizes existing entities such as person name, time, organization name, and place name.