“My research interest,” says Dr Stephan Ludwig, senior lecturer in the Department of Marketing and Business Strategy at Westminster Business School, “is in message design. I’m looking into how marketing messages are designed, how they influence consumers’ decision-making behaviour, and reflect on how consumers feel”.
Big data, social media and customer reviews
“It’s a broad topic,” he says, “but I’m particularly interested in the big data, social media environment which has become very prominent over recent years.”
“The consumer now has a voice, they can say what they think they can tell or share their experiences with other interested customers. It makes a very interesting environment where the customer suddenly has all the power they can possibly imagine. No longer are you alone with your experience, but rather, everyone can hear and also react to it.”
After completing his PhD at Maastricht University in the Netherlands, Stephan worked as a consultant for a few years, but returned to academia because he missed teaching and “the liberty of choosing the projects I want to work on”.
His current research projects include looking at what can be learned from how customers formulate their experiences and communicate with each other.
“What can we learn about the customer experience from that? How do other consumers react? And, from a company’s perspective, how do messages need to be formulated to be more impactful and be heard by more people?”
Social media and smarter data
It’s research that can be applied directly to real world situations. “A lot of companies,” Stephan says, “just pile on money into social media people. Basically as long as you have a Facebook account and you’re 18 years old and you know how to write a post, you’re hired.” That, he reckons is “simply because we’re baffled with this overwhelming amount of data, and volume of messages flowing towards – and between – companies.”
“So, the message design aspects of my research help companies to sift through that data and make it smarter data, usable data in a quick, easy-to-do fashion. For example, if you think about launching a new product, or you have launched a new product, and you want to know how people experience it, you’re not going to read all the tens of thousands of Facebook messages and tweets to find that out, and then try to compile it into a usable chart, but rather what you want is quick, quantifiable information. That’s what my research does: provide companies with an overview of what’s going on and how they can quickly assess it.”
Stephan achieves this by using text analysis and text mining software and techniques. “Text analysis and text mining are a bit of a mixture of a quantitative and qualitative techniques,” he says. “So, we used to have linguistic researchers who would code a text or conversation for particular aspects, such as the emotion of the person writing. Who wrote the text? Were they feeling sad or good? Are they highly motivated?”
Now, data modellers and software developers create text mining dictionaries. “So, for example,” Stephan explains, “we would have a text mining dictionary consisting of lots of happy emotion words, and one for negative emotion words. Then, text mining algorithms run over however many texts you want – there can be millions, there’s no limit – and count how many happy and negative emotion words are used, and you can automatically tell, more or less, whether the person who wrote it was happy or not, simply by the amount of positive or negative emotion words they used.”
Software that catches liars
Stephan is currently working with Tom van Laer at Cass Business School developing software designed to assess the probability that the writer of a text-based communication intended to deceive the recipient. Something that is likely to prove highly useful for insurance companies, amongst others.
Watch Stephan talk about his research
Academic papers by Stephan
Ludwig, S., De Ruyter, K., Mahr, D., Wetzels, M., Brüggen, E. & De Ruyk, T. 2014. Take Their Word for It: The Symbolic Role of Linguistic Style Matches in User Communities. MIS Quarterly, 38, 1201-1217.
Ludwig, S., De Ruyter, K., Friedman, M., Brüggen, E., Wetzels, M. & Pfann, G. 2013. More than words: The influence of affective content and linguistic style matches in online reviews on conversion rates. Journal of Marketing, 77, 87-103.
Ludwig and de Ruyter (2016), “Decoding social media speak: Developing a speech act theory research agenda”, Journal of Consumer Marketing, forthcoming.
3 text analysis must-reads
Text Mining and its Business Applications – Niladri Biswas in CodeProject
Improving the Consumer E-commerce Experience Through Text Mining – Luke Wallace for Software Advice
How Traders Are Using Text and Data Mining to Beat the Market – Roy Kaufman in TheStreet
Social Media workshops at Westminster Business School
Coming soon: Social Media for Business Innovation