A new study by Professor Kübler just published in the Journal of Interactive Marketing shows how to rely on user generated content from Facebook to measure classic consumer mindset metrics such as brand awareness, brand liking, brand consideration, purchase likelihood or customer satisfaction.

“Accounting for the importance to have daily access to these mindset metrics and to give managers a chance to continuously monitor and control how consumers perceive a brand, we looked into and compared different techniques that may allow measuring brand sentiment with the help of what consumers write about brands in specific social media channels,” explains the young MCM scholar.

The paper „Social Media's Impact on the Consumer Mindset: When to Use Which Sentiment Extraction Tool?“ authored together with Anatoli Colicev from Bocconi University in Italy and Koen Pauwels from Northeastern University in Boston/USA explores a rich set of sentiment extraction techniques and finds that machine learning based sentiment extraction tools such as support vector machines are especially helpful to measure brand sentiment.

“Our identified tools can help managers replacing classic survey based brand sentiment metrics with earned social media content. This brings the advantage that data is not only free of any potential survey based biases, but that information on how well the brand is doing, how many consumers know and like the brand, and how many customers are satisfied with the brand or services are available on a continuous base. This allows managers not only to track brand health, but also to easily and timely inspect how marketing activities such as e.g. ad campaigns or price promotions affect the consumer mindset,” concludes Professor Kübler.

The paper is available here as Open Access and can be downloaded for free by anyone.