Polytechnic University of Valencia Congress, CARMA 2020 - 3rd International Conference on Advanced Research Methods and Analytics

Font Size: 
Combining content analysis and neural networks to analyze discussion topics in online comments about organic food
Hannah Danner, Gerhard Hagerer, Florian Kasischke, Georg Groh

Last modified: 14-05-2020


Consumers increasingly share their opinions about products in social media.
However, the analysis of this user-generated content is limited either to small,
in-depth qualitative analyses or to larger but often more superficial analyses
based on word frequencies. Using the example of online comments about
organic food, we suggest a three-step methodological approach of how latest
deep neural networks can scale up the insights of qualitative analyses. First, a
qualitative content analysis defines a class system of opinions. Second, a pre-
trained neural network, the Universal Sentence Encoder, uses this class system
to automatically classify the same data by finding similar opinions. Third, the
automatic classification results are evaluated based on several criteria. We
find coherent results of qualitative and automated classification proving the
ability of Universal Sentence Encoder to classify text. After this validation,
Universal Sentence Enconder can be used to classify larger data sets on
organic food. The suggested approach allows to scale up sample size while
maintaining the detail of class systems provided by qualitative content
analyses. The approach can be applied to different domains and support
consumer and public opinion researchers as well as marketing practicioners
in further uncovering the potential of insights from user-generated content.

Full Text: PDF