Robert Kohtes – författare

Diploma Thesis from the year 2012 in the subject Business economics - Miscellaneous, grade: 1,7, University of Cologne (Lehrstuhl fur Handel und Kundenmanagement), course: Business economics, language: English, abstract: The growing number of user-generated content online has led to a huge amount of data that can be used for scientific research. This thesis investigates the prediction of certain human-related events using valences and emotions expressed in user-generated content with due regard to past and current research. First, the theoretical framework of user-generated content and sentiment detection- and classification methods is explained, before empirical literature is categorized into three specific prediction subjects. This is followed by a comprehensive analysis including a comparison of prediction methods, consistency, and limitations with respect to each of the three predictive sources. It was found that the research results and prediction accuracies analyzed significantly differ from each other according to the sources of data and prediction methods they employed. In addition, a comparison of fine-grained and coarse sentiments as predictive data sources shows that fine-grained sentiments improve prediction accuracy. Theoretical concepts are used also for evaluation purposes because empirical data on fine-grained sentiment approaches is scarce.

Auf der Basis einer fundierten empirischen Analyse weist Robert Kohtes die Wirkung von Intramarkenimagekonfusion am Beispiel der Automobilindustrie nach. Es wird gezeigt, dass sich die Verwirrung des Nachfragers aufgrund zu ähnlicher, unklarer oder unglaubwürdiger Produktmarken innerhalb einer Geschäftsfeldmarke sowohl negativ auf die Geschäftsfeldmarke als auch die Kaufintention des Nachfragers auswirkt. Praxisrelevante Handlungsempfehlungen zur Vermeidung von Intramarkenimagekonfusion für das Markenmanagement schließen die Arbeit ab.