|
JPM Kübler

Socially (IR)Responsible Algorithms: How the internet can betray our privacy - Seminar Wrap-Up

Social media has changed the way we interact and communicate. It provides us with great opportunities to meet with friends and colleagues all over the world. It delivers interesting information on a daily base and makes us continuously discover new things. It keeps us up to date and helps us to navigate through a rocky and often overwhelmingly complex world. By nurturing us with the necessary knowledge and giving us the needed bonds with our peers, social media has become a vital part of our daily life. 

And still, as our own digital fingerprint within the social media realm may tell complete strangers more about us than we are willing to share with the public, it bares the potential to horribly betray us. In 2013, Kosinski et al. published a widely noticed study in the Proceedings of the National Academy of Science that demonstrated how individual likes of Facebook fan pages can be used to predict personal traits such as our individual age, gender, political and sexual orientation, eating and drinking habits or our very own heritage and racial profile. While the authors intended to warn the public about the possible side effects of the happy social media universe, dark forces made profit from these insights and started to collect information of what people liked on Facebook. Alexander Kogan’s app “This Is Your Digital Life” used a loophole in Facebook’s API and crawled information about following behavior from more than 80 million Facebook user profiles -  in many cases even without the specific consent of the involved profile owners, as the app did not only access the information of the specific app user, but also of all his/her friends. Kogan then shared this data with Cambridge Analytica which claims to have used the data for various political campaigns within the context of the Brexit referendum, the 2016 Republican primaries and the subsequent 2016 US Presidential elections. While few hard facts are known about what Cambridge Analytica could achieve with the data, the company’s CEO Alexander Nix explained in various keynotes that Cambridge Analytica similarly used the data to predict personal traits and to use this information subsequently to target users with specifically designed political advertisements.

In the aftermath of the 2016 US presidential elections and its mostly unexpected outcome, Cambridge Analytica’s activities have been put into the spotlight of public attention. While the company has been seized for malpractice, the heat on its stakeholders and Facebook increased. Five years after the initial scandal, public awareness about the possibility to predict personal traits with the help of a social media user’s footprint has cumulated in heavy media coverage and multiple widely acclaimed documentaries such as e.g. “The Great Hack” or “The Social Dilemma”.

Despite the large public attention to the possible mis-use of social media data, we see social media engagement still to increase. While Facebook usage declines, younger target groups switched their attention to other platforms such as e.g. Instagram or TikTok. Many users believe that the changes in structure and communication style make these platforms less vulnerable to information betrayal. And even though communication styles switched from text-based information more to images and videos, both popular platforms require users to follow accounts to receive content and information. 

Still, what many users seem to ignore or not realize, is that information about who is following an account is still publicly observable. This implies that one may again collect user followership information and pair this information with personal traits to build a prediction algorithm that forecasts a user’s personal traits based on the accounts a user is following on a platform. In other words: What Kosinski et al. showed in 2013 may still be very feasible in today’s new social media world.

Therefore, we decided to use one of our very own research seminars at the MCM to understand how much personal information of a user can be predicted with the help of his or her social media usage. To do so, we first replicated the study by Kosinki et al. (2013) in the context of Instagram. While Kosinki et al. could rely on large sample of 40,000 participants, we needed to constrain ourselves to a much shorter sample. So, we conducted a survey with approx. 2,000 Instagram users in which we asked participants to indicate which popular accounts they followed on Instagram. Users could choose between 200 accounts. Furthermore, we asked participants to answer a survey that measured, amongst other factors, personal traits (like e.g. the 5-factor OCEAN model), sexual orientation, gender, age, drug usage, political preferences, race and location within Germany. Following Kosinki et al. (2013) we then predicted the traits with the help of information on which accounts participants followed on Instagram. Relying on holdout sample validations, we can show - even though our sample is much smaller than the one of the initial study – that we similarly well predict major personal traits. Our replication thus already shows that once you have enough personal information and pair it with social media data, predictions become easy. In other words, with enough survey data, we could also deliver reliable predictions for social media users who did not participate in our study. 

The video below gives a great summary of the survey work and the prediction accuracy obtained by our students. 

One may now claim that social media data only becomes dangerous once one has a large enough training data set with enough personal information. Or in other words: If you don’t have enough survey data, you can’t predict something. This made us question if you really need survey data to obtain enough personal information to feed the follower prediction model. So we started looking around for alternative personal information sources which we may use to train our algorithm. Surprisingly, we found that many Instagram users happily share such information with the public. Not only that specific hashtags or types of posts may allow you to predict someone’s preferences, many users also often provide more sensitive and concrete information within their profiles. Consequently, we crawled Instagram user bios and looked for sensitive information. We were awed to find that many users happily share information on where they live, their birth year or age, gender, their main interests, sexual orientation and sometimes even their drug habits right in their Instagram bio. Crawling more than 200,000 user profiles we similarly built a large training set and combined the bio information with information about which public or well know accounts these people followed on Instagram. Again, we replicated the Kosinski et al. (2013) approach and developed a predictive model. The holdout sample validation indicated that the predictive power of these models was comparable to the findings of our replication study, showing that training the algorithm with publicly available information instead of survey data delivers similar results.

Just to understand what we could predict and how we adapted our approach to the new data sources within Instagram, check the two following videos.

All participants were similarly shocked to see that even though public awareness of social media’s potential of information betrayal is high, people seem to not understand how easily critical information can be acquired and used to deliver valid and reliable predictions of someone’s private traits. 

A key issue here is that one does not even need any more survey-based information for training. Instead, training data may be directly obtained from privacy insensitive users which may then finally be used to predict personal traits of people who in fact do not share their personal traits, but become predictable through what they like and follow on social media.

Read more about Socially (IR)Responsible Algorithms: How the internet can betray our privacy - Seminar Wrap-Up
|
Raoul Volker Kübler

Made in Münster Clubhouse Talk Vol1

Kampagnen Effizienz in Social Media - Ein Überblick

🤝 Thanks a lot again for tuning in and showing interest into how to manage social media campaign efficency with the help of an empirical approach. We agree that it is almost impossible to grasp all the exciting insights we talked about in the little time we had. Therefore we thought it might make sense to provide you with some links to the discussed studies so that you can read things again. 

Please find below the three main studies we referred to👇 . All of them should be publicly available

Bond et al. (2012)
deVries, Gensler, and Leeflang (2012)
Kupfer, Pähler vor der Holte, Kübler, and Hennig-Thurau (2018)

Some of our general Key Take Aways from today's talk:

  • Social Media matters! There is a palette of empirical evidence that social media activities enhance people's voting behaviour. 
  • Social Media does not necessarily shift preferences. There is some first evidence for that but we are far from really understanding, how this can be achieved! 
  • Political advertising (in general though!) has been shown to substantially increase voter turnout, however it only explains 1% of the variance of political preferences!
  • Social Media engagement and peer pressure drives voting intention! 
  • Engagement  is thus more important than simple reach!
  • Engagement on social media depends on classic marketing! Segmentation, Targeting and P O S I T I O N I N G are thus key! 
  • Interactivity and vividness have been shown to drive enaggement. Activate your audience through content that allows interaction! 
  • If you rely on the help of influencers, testimonials or other co-brands, ask them to provide exclusive and authentic content that provides a clear call to action!
  • Don't assume that things immediately work. A/B tests and other forms of online experiments are great tools to better understand what works with your target group!

 

 

 

 

 

Read more about Made in Münster Clubhouse Talk Vol1
|
JPM Kübler

Interview with Prof. Raoul Kübler about Sponsoring of Offshore Sailing and Success of German Vendee Globe Sailor Boris Herrmann published by segelreporter.com

MCM Professor Raoul Kübler was interviewed by Germany’s leading online sailing magazine segelreporter.com. With Boris Herrmann being the first German sailor to finish the world’s hardest solo around the world race, sailing gained in popularity and enjoyed a substantial increase in screen and media time. 

In his interview, Professor Kübler discusses the reasons behind the growing public interest in offshore sailing and how Boris Herrmann successfully used social media to engage with a worldwide audience to promote his campaign but also sailing in general.

He concludes that the accessibility of Boris Herrmann, the high degree of authenticity and emotionality was a huge benefit for the campaign and helped Boris Herrmann and his team to sustainably engage a large audience.

“In times of a worldwide pandemic with people being locked at home, Boris brought a true adventure on everyone’s screen and allowed his followers to race with him around the globe,” explains the marketing scholar and passionate sailor. While sailing may have been perceived previously as a privileged and posh sport, Boris understood to communicate that his campaign is not about privilege or money, but about nature and adventure.

This positioning was especially helpful to create a meaningful touch point. By communicating that more people have climbed Mount Everest or have been in space, than people having finished the Vendee Globe race, Boris successfully accentuated his challenge and amazed a non-sailing audience.

Sailing provides many interesting opportunities for media and corporate sponsors, Professor Kübler explains. However, it is yet unclear how companies can benefit from the public attention and awareness. “Sailing sponsoring has been shown – like other sponsoring campaigns – to be especially suitable for new product launches”, the MCM scholar explains. Companies have however to understand how to match their own brand and product with the story and core values of the sponsored sailing campaign. British sailor Alex Thomson and his long standing collaboration with German fashion brand Hugo Boss have shown that success in sailing is not necessarily key for that. Instead, clear storytelling and having an integrated positioning that combines the brand’s core values with the adventure of the sailing team are essential.

This is in line with a social media study published in 2018 in the prestigious Journal of Marketing by MCM scholars Ann-Kristin Kupfer, Nora Pähler vor der Holte, Raoul Kübler and Thorsten Hennig-Thurau. The study shows by analyzing thousands of Faceook posts of movie actors that brand collaborations on social media can successfully increase product success, when both parties well integrate and social media actions are authentic, exclusive and engaging. 

The MCM scholar therefore recommends brands who are willing to engage with sail and sport sponsoring to conduct thorough market research to develop a clear storyline and discover relevant touch points with their partner brand’s audiences.

The Vendee Globe is the world’s most prestigious and most challenging offshore race. It starts and ends every four years in Les Sables-d'Olonne (France) and requires participants to circumnavigate the globe non-stop and alone. In France, it attracts millions of visitors and is considered to be a prime-time sport event comparable to the soccer world cup or the Olympics. 

The interview was recorded shortly before Boris Herrmann’s collision with a Spanish fish trawler 90 miles ahead of the finishing line, costing him a podium place and putting him back to 5th place overall after having been part of the leading group for more than 24,000 nautical miles. 

The interview in German can be found here.

The referenced study in the Journal of Marketing investigating brand collaboration effects on social media can be found here.

 

 

Read more about Interview with Prof. Raoul Kübler about Sponsoring of Offshore Sailing and Success of German Vendee Globe Sailor Boris Herrmann published by segelreporter.com
|
JPM Kübler

CLUBHOUSE TALK VOL1: Why do so many struggle with measuring marketing RoI

Some additional info to my talk with Bendix Hügelmann on January 20, 2021
Clubhouse Vol1
Clubhouse Vol1

 It was a great pleasure talking to you all and very inspiring to see 💡  that our topic really matters to a lot of people.

So I wanted to provide everyone 💁‍♂️ with some brief summary and some additional material so that you can start your very own return on invest journey and finally understand what drives your very own marketing performance.

First and foremost, don't worry! Even though things may at the beginning look a bit wicked, this is less about statistics and mathematics than about clear and rational thinking!

Second: Don't listen to anyone but your own curiosity! There is a lot of hype out there that will tell you which numbers or methods are key. Some people will even tell you that it is simply impossible to measure ad impact and that advertising might now even show any impact at all (like Dr. Fou points out here: https://www.forbes.com/sites/augustinefou/2021/01/02/when-big-brands-sto...). Others will try to sell you their very own approach or tool. Both sides will likely try to fool you.

So don't get fooled and try to be a good German by following Kant's definition of enlightment and try to excerpt from your self-inflicted immaturity instead!

Marketing research has spend a lot of time and energy to measure advertising lift. There is a sophisticated palette of tools and techniques available to quantify the impact of advertising and other marketing activities. I will post some articles, which I personally find to be inspiring below. Most of them are open access, for some of them you will need to get access through a university library. 

While you read through these sources, keep some basic rules in mind!

First rule of the marketing RoI Club (no I don't mean you should not talk about the club):

0️⃣1️⃣ Don’t be fooled by numbers! Don't run for high conversions or clicks. Don't focus on the things that happen on the way. But focus on the outcome. In many cases in marketing this may be sales. In other settings this may be polls (politics) or share price (finance). Once you understand what to focus on, you will also understand at which other variables you want to look at, when trying  to understand what drives your performance variable of interest and how these things work together!

0️⃣2️⃣ Don't take it easy! Only because some ads show magnificent numbers or your numbers seem to tell you that one thing drives them all, it doesn't need to be so. Last click attribution is often confused as a performance measurement tool. But it isn't! In fact last click attribution is like blaming your last drink the night before for your headache. We are living in a complex world. Things interact. And you certainly had a drink or two before, which may similarly explain your current state of affair. The trick is to understand how things worked together, and how much the first prosecco  made you stay at the bar and have another drink. And how this again affected your decisions to move to shots an hour later. Once you understand the dynamics across a consumers decision process and how these things work together over time you will be able to really quantify the individual impact of each drink you had. Or all the ads you booked!

0️⃣3️⃣ Remember again, about what we talked. Once you have your performance variable, identify performance drivers. These will point you on the performance indicators, using analytics and models, you will be able to identify lead performance indicators and comparing impact numbers you will finally be able to identify your personal Key Performance Indicators. And again, don't trust other people who claim to have found the one and all KPI. Remember, some people like Tequila. Others Rum. And some even like Whiskey. At the end of the day, it is about your individual model. 

0️⃣4️⃣ Once you have your KPIs, try to understand what is driving them. This means you can move forward, by becoming more granular with your analysis. You know that number of comments matter from your model when it comes to polls? So the next question is then, what drives commenting behaviour. Add the necessary information to your model. Code each post into topics. Use text mining tools to understand how emotions influence comments. Continue to climb down the ladder. You will soon learn that this game never ends. It only makes you smarter!

0️⃣5️⃣ Keep being critical and curious. Models are only one part of the equation. Experiments are the other. You believe you identified something? Try it out. Use some posts to play with the identified drivers and see if your idea is working. If not, go back to step 4 and see what other factors may cause your variable of interest. 

I know at the beginning this all feels overwhelming and complicated 🙈. At the end you will realize that this isn't rocket science 🚀. Still you will see that once you dive into this world, the sky is the limit 🛰🛸! To begin your journey, I recommend to start having a look at the attached readings. If you are not scared by greek symbols and math, start with the journal articles. If you prefer more verbal explanations and feel that you would like to first understand the logic behind it, start with Koen Pauwel's book (the third reference). He walks you gently through each topic and helps you to develop your very own marketing return on invest model. At the end you will even be able to develop your very own dashboard to monitor and track your KPIs. 

  • De Haan, E., Wiesel, T., & Pauwels, K. (2016). The effectiveness of different forms of online advertising for purchase conversion in a multiple-channel attribution framework. International Journal of Research in Marketing, 33(3), 491-507.
  • Peters, K., Chen, Y., Kaplan, A. M., Ognibeni, B., & Pauwels, K. (2013). Social media metrics—A framework and guidelines for managing social media. Journal of interactive marketing, 27(4), 281-298.
  • Pauwels, K. (2014). It's Not the Size of the Data--it's how You Use it: Smarter Marketing with Analytics and Dashboards. Amacom

I hope you enjoyed this very brief intro. If you like to know more, just drop us a mail and join us for our next clubhouse talk next week!

 

Read more about CLUBHOUSE TALK VOL1: Why do so many struggle with measuring marketing RoI
|
JPM Kübler

Junior-Professur für Marketing & Marketing Analytics sucht wissenschaftliche/n Mitarbeiter/in

An der Junior-Professur für Marketing & Marketing Analytics der Westfälischen Wilhelms-Universität (Marketing Center Münster, Fachbereich Wirtschaftswissenschaften) ist zum nächstmöglichen Zeitpunkt zunächst befristet auf 3 Jahre eine Stelle mit Dreiviertel der regelmäßigen Arbeitszeit einer wissenschaftlichen Mitarbeiterin/eines wissenschaftlichen Mitarbeiters zu besetzen. Mehr Informationen entnehmen Sie bitte der Stellenausschreibung

Wir freuen uns auf Ihre aussagekräftige Bewerbung!

Read more about Junior-Professur für Marketing & Marketing Analytics sucht wissenschaftliche/n Mitarbeiter/in
|
JPM Kübler

How empathy helps to create successful advertising campaigns – Guest lecture by Grabarz & Partner

In response to the positive feedback for their guest talk last year, Grabarz & Partner again followed the invitation by Professor Kübler and joined the lecture „Integrated Marketing Communications” on July 6, 2020. During their 90-minute presentation, Reinhard Patzschke, CEO Consulting at Grabarz & Partner, and Bastian Goldschmidt, Head of Strategy, showed how they convert social trends into successful advertising campaigns. Grabarz & Partner belongs to one of the most successful German advertising agencies and has just been awarded as one of the „Top Ten Creative Agencies of the Decade”. They are working together with companies such as Porsche, Volkswagen, Fielmann or IKEA. 

In their presentation, the two advertising specialists argued that in today’s so-called “second era of enlightenment” advertising agencies do not only have a responsibility for brands, but also for society. Thus, they underlined the importance of empathy which helps them to develop campaigns which meet the current zeitgeist and to eventually cut through the advertising clutter. When planning new communication concepts, the company checks whether advertising and information campaigns are positively or negatively affected by these topics or if they lead to new communication potentials. To better illustrate their statements, both speakers brought along a collection of carefully selected trends currently affecting society which they summarized in five different statements including Shit is getting personal, Let’s talk about sex or Let’s get stoned. A little.

As the students of the “Integrated Marketing Communications” class are to develop an integrated communication campaign for different Münster-based businesses which face challenging times due to the ongoing COVID-19 crisis, the presentation has been followed by a vivid discussion. Students had the possibility to exchange first ideas regarding their campaigns and to discuss how their project cases relate to the different trends presented. 

Despite this year’s presentation could only take place in a virtual environment, one could sense the great passion Grabarz & Partner puts into its work. Also, the camera in front of which Reinhard Patzschke and Bastian Goldschmidt presented, allowed for insights into the premises of the advertising agency and gave an idea of the pleasant working atmosphere which otherwise would have remained hidden. 

All in all, students were very enthusiastic about the talk as it picked up the theoretical elements from the lecture and transferred them into a practical context. Hence, it not only helped the students to better understand the different lecture contents, but also underlined the high relevance of marketing education in Münster. 

Read more about How empathy helps to create successful advertising campaigns – Guest lecture by Grabarz & Partner
|
MCM

Virtual Guest Talk

“How do we conduct Market Research at Douglas?” by Dr. Vanessa Junc and Christian Koldehoff

On Tuesday, May 19, 2020 Dr. Vanessa Junc (Senior CRM Analyst) and Christian Koldehoff (Team Lead Global CRM Analytics) held a virtual guest talk in Market Research providing additional practical insights for students during this summer semester. During the presentation, the two representatives of Europe’s No.1 beauty destination introduced their loyalty card program and elaborated on the benefits of CRM data analytics. Students were encouraged to see how data gathering and data management lead to a better understanding of the customer and ultimately a better brand performance along the three already studied concepts of descriptive, exploratory, and causal research.

In a first step, Dr. Vanessa Junc and Christian Koldehoff briefly outlined descriptive research which aims at generating customer insights by using information systems. Keeping track of purchase patterns or demographics of customers is indispensable for measuring and analyzing brand and/or customer performance which helps them and their team to improve the customer experience at Douglas. Special attention was also paid to the visualization of data. According to Dr. Vanessa Junc and Christian Koldehoff, an adequate visualization is key in communicating insights of customers to different stakeholders. Understandability and easy interpretation can be for example ensured by interactive reporting tools or dashboards. In a second step, the Douglas’ representatives turned to exploratory research and the opportunities in customer segmentation. Dividing customers in different groups based on their demographics, preferences or brand purchase behaviors allows to appeal them in a more individualized way. Based on customer segmentation, simple A/B testing can be conducted in terms of causal research in a third step to measure the effectiveness of segment-specific campaigns vs. a one-to-all approach. Results revealed that segment-specific newsletters not only show a higher open rate but also increased sales. Generally speaking, CRM data analytics lead to an improved brand performance and at the same time serve as a new basis for managerial decision making.

In a later discussion, students were able to raise their questions regarding Big Data, Machine Learning and sustainability initiatives at Douglas taking advantage of the interactive character of the guest talk. The two representatives emphasized the increasing importance of these trends specifically for Douglas and the entire beauty industry in general. We thank Dr. Vanessa Junc and Christian Koldehoff for their valuable practical insights into how analytical CRM is conducted at Douglas.

Read more about Virtual Guest Talk
|
MCM

Marketing Students from Münster Win International Advertising Award!

On November 28th 2019, a group of MCM marketing students secured a remarkable third place in the talents category of the prestigious Neptun Cross Media Award in Hamburg. The students had to develop an advertising campaign for the Münster lemonade brand liba as a final project for this summer’s “Integrated Marketing Communications” (IMC) class hold by MCM professor Raoul Kübler.

The project turned out to that exciting that the instructor decided to submit the campaign to the international advertising show “Neptun” that awards best multi-channel campaigns each year. With good reason: even though the talents section featured more than 18 excellent international submissions, the Münster students secured at the end a prestigious 3rd place.

“The efforts and performance of our team can not be judged high enough,” explains Professor Kübler. “The first two places in this year’s award went to submissions from the Miami Ad School. We were the only classic business school in this year’s award. All other submissions were similarly based on outstanding creative ideas. However, the jury was especially delighted by the analytical work of our students and how the team translated these research insights into a convincing and creative cross-media campaign that integrated the key message in multiple, different media channels”.

The campaign "liba for your city" focuses – based on the extensive marketing research and field studies conducted by the MCM students – on a rather unconvential expansion strategy that targets cities like Essen, Krefeld, Bonn and Wuppertal instead of major metropolises such as Hamburg or Düsseldorf by appealing to local pride and regionalism. Funny headlines such as “Better from the Kiosk than from big enterprises”, “Better Ruhr than Rimini” or “Better Burg Linn than Berghain” help the students to catch interest and awareness. Relying on regionalism the campaign further fosters curiosity and drives test-sales for an alternative and sustainable lemonade.

Also liba founder and manager Benjamin Heeke is delighted: “We congratulate the student’s team for their big success. We were also fascinated by the many ideas developed by the other teams for our brand during the IMC class. We will now directly contact all students and discuss how we can use the many ideas to better promote our product”.

Defne Deneri, Jessy Hauser, Niklas Westernberger, Felix Gößling, and Kevin Goy Ramos also conclude that the many efforts taken for the project were worth it: “It is great to see that all the different theoretical insights and concepts which we encountered during the IMC class were truly helpful to develop a power- and successful campaign, that did not only convince the liba management, but also delighted the leading experts of the international award jury.”

You also can watch a short campaign video here:

Read more about Marketing Students from Münster Win International Advertising Award!
|
MCM

New publication by Professor Kübler: Social Media's Impact on the Consumer Mindset: When to Use Which Sentiment Extraction Tool?

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.

Read more about New publication by Professor Kübler: Social Media's Impact on the Consumer Mindset: When to Use Which Sentiment Extraction Tool?