Essays on text mining for improved decision making: Thesis contains seven Fraunhofer INT studies

Data mining is defined as the process of extracting patterns from data. Thus, it is used to transform this data into information. A specific area of data mining is text mining or text data mining as the process of deriving high quality information from texts (unstructured data). Text mining structures the input text in a first step, it identifies new and unseen patterns within the structured textual data in a second step, and in a third step, it evaluates and interprets the results. Closely related to text mining is web content mining as process of deriving high quality information from the content of web pages. In total, the dissertation shows how methods from text mining and from web content mining can be used to support marketing professionals by improving marketing decision-making. The methodologies are presented in several studies where relevant textual information is analyzed that can be found in different sources (e.g. in web pages, documents, research papers, articles in technical periodicals, reports, etc.). This dissertation consists of seven studies. In two studies, this dissertation supports marketing professionals by identifying profitable customers and companies. This dissertation contains further five studies, which contribute to methods from text mining into the marketing - R&D interface of the new product development process. Sect. 5 describes the research objectives of these studies as well as the methods from text mining and from web content mining that are used in this doctoral dissertation. Sect. 6 summarizes the main findings of the different studies, while Sect. 7 relates to the limitations and suggestions for further research