Showing posts with label facebook likes. Show all posts
Showing posts with label facebook likes. Show all posts

Tuesday, March 25, 2014

New Brand Assets: Where are we going?


"We show that easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of highly sensitive personal attributes including: sexual orientation, ethnicity, religious and political views, personality traits, intelligence, happiness, use of addictive substances, parental separation, age, and gender. The analysis presented is based on a dataset of over 58,000 volunteers who provided their Facebook Likes, detailed demographic profiles, and the results of several psychometric tests."

Kosinski et al. 2013 (The Psychometrics Centre, University of Cambridge)


Like. Comment. Engage. Sponsored post again? Uhm.. Is your behavioral targeting ok? No?It's fine. Don't worry. Numbers are fine.

How have brands embraced digital ecosystems like Facebook as a key marketing channel to drive engagement and brand awareness? Let's use FB like waveforms as a metric of brand engagement and let's illustrate some examples of FB like pages:

Multinational retail corporation with 35M likes
Ivy League management magazine:
A worldwide branded commodity

A multinational sports company
Leading Telecommunications company in Greece-edited

Leading retail operator in Greece
It seems that these waveforms are similar to a manipulated oscillograph signal where the peak comes in "Sponsored Campaigns" periods and then to zero, till the next paid campaign. 


There are tons of examples like these. Off course, some of these effects could be explained by deeper analysis of econometric advertising models, mentioned here, but is this the best we can do with these new media? Where is organic traffic? Does paid traffic have a decent ROI in terms of brand engagement?


It depends.


I believe that the virtual digital economies which are developing as we speak will reshape the landscape of marketing as we know it. But do marketers do their best in order to engage with the customer, as brand ambassadors? The images above indicate that apart from the times that we press the button "Boost Post", things do not go very well in terms of brand engagement. Further KPI's, like numbers of comments and shares, retweets and favorites, per brand page, analyzed with statistical tools, should easily verify this hypothesis. I understand that perhaps, the higher the numbers, the higher is the brand perception and other key brand assets, but are the results discrete and measurable? 


In the long term, does the world have enough strategists to make optimum use of the new technologies and channels of communication?


For the time being we have:

  • Google, Facebook, Twitter charging and gaining billions for "awareness" and "engagement".
  • Overvalued IPOs, overnight millionaires, questionable business models, startups offering frivolous services, fake engagement tools and similar services.
  • Marketers trying to deliver actions with ROI but frequently unable to achieve optimum brand engagement, let alone incremental sales or other corporate goals.
  • 3B customers who are now online but have the same purchasing power that they would have if digital marketing wouldn't exist in a parallel universe.
  • Academics trying to follow up and model consumer behavior versus both real-life and digital marketing stimuli as technology advances.
A nice bubble? I think, yes.

How would Aristotle structure his philosophical pillars if he was writing his "Athenian Constitution" in his free time while working as a Chief Marketing Officer for Facebook or Google?


21st century. Who will pay for the news?

Tuesday, September 17, 2013

A Facebook for my Brand : Fan Pages and KPI's


Facebook fan pages can be regarded  as a virtual brand community. They are specialized, non geographically bound communities and they are based on a structured set of social relations among admirers of a brand. Therefore the theoretic explanations for a brand community are also suitable for explaining the fan page phenomenon. Social identity and  symbolic interactionism theories show that interaction with members of a reference group can lead to a strong feeling of belonging to this group (in this case the brand community) which in turn can lead to stronger buying behavior and positive brand attitude.

But how can we be sure that being a member of a facebook fan page has an impact on a brand admirer's buying behavior and brand attitude? Researchers from the University of Mannheim actually designed an experiment and assumed that members of the BMW fan page show stronger buying behavior and brand attitude than non-members and that within members, buying behavior and brand attitude are even stronger for active members than for passive ones.In order to carry out the experiment they conducted an online survey among 840 BMW admirers.

The BMW Fan Page Survey

Membership and interaction were expected to influence psychographic dependent variables (brand loyalty, brand commitment) and economic dependent variables (purchase intention, willingness to cross-buy and  positive word of mouth). Willingness to cross-buy was polled in three categories, which were lifestyle products (e.g. apparel), financial services (e.g. leasing or insurance offers) and original BMW spare parts. Purchase intention was polled in two categories, which were automobiles and BMW car repair services. In order to analyze the influence of membership and interaction, two separate experiments were carried out. In the first study, respondents were split into  members (n=210)  and  non-members (n=630) according to the membership of the German BMW fan page. The non-members became the control group and members became the experimental group.

Furthermore, members had to answer questions about their usage of the BMW fan page . Using these responses, a weighted interaction level was determined for each member. A cut-off value was then applied to the weighted interaction level to classify members of the BMW fan page either in passive or active members. While passive members don't or rarely interact with the fan page, active members display a higher level of interaction.


Influence of Membership

In order to analyze the influence of membership on the dependent variables,  the nonmembers and members of the Facebook fan page were compared with each other. Non-members (n=215) were recruited in BMW internet forums to make sure they are admirers of the brand. In order to be able to analyze variances of members and non-members, the groups need to be about the same size (max factor 1.5). That is why a sample of n=315 was randomly drawn out of the total number of the BMW fan page members (n=630).

Then the data was analyzed using a multivariate analysis of variance (MANOVA) in order to examine differences between the responses of the two groups. The mean values were calculated and compared between the groups to evaluate whether membership and interaction do have an influence on the dependant variables. The F-Values of MANOVA indicate that there are differences between the groups. These values ranged from F = 23,608 to 89,195 woth significant values of p=0.00, allowing to proceed with the interpretation of MANOVA.


A comparison of the mean values of the two groups proved that there are significant differences between non-members and members  of the BMW fan page for all 10 dependent variables. Specifically, membership has a strong positive influence on the affective variables brand  trust, brand  loyalty, brand commitment and positive word of mouth (∆ between +0.646 and +0.733, average ∆ = +0.675). Its influence on the conative variables brand satisfaction, purchase intention (for both product and repair services), and willingness to cross-buy (for lifestyle products, financial services and spare parts) is also strong (∆ between +0.395 and +0.985, average ∆ =  +0.682). The highest difference of mean values exists for  purchase intention (∆ =  0.985)  and willingness to cross-buy (∆ = 0.923).

Influence of Interaction


Having analyzed the influence of membership, the next step was to look more closely at the members of the BMW fan page, with the objective of determining whether the level of interaction on Facebook fan sites has any impact on the dependent variables. For this purpose, the four types of interaction with the fan page (writing posts, clicking the “Like” button, uploading photos or videos and sharing photos or videos with other users) were weighted to determine the level of interaction. Based on this level, members of the BMW fan page with a low level were then classified as passive and with a high level of interaction as active members.


The two groups were also analyzed using a MANOVA. Unlike the first pass, the second one did not deliver significant F-values for all 10 constructs. While most of the constructs had values between F = 4,815 to 23,668, purchase intention (for both product and repair services) and brand satisfaction failed to deliver satisfying p-values (p = 0.065, 0.758 and 0.425).


The comparison of the mean values of the two groups makes it clear that the significance of the MANOVA F-tests stem from the differences between the groups. Specifically, interaction has a positive influence on the affective constructs brand trust, brand loyalty,  brand commitment and positive word of mouth (∆ between +0.160 and +0.316, average ∆ = +0.233). Its influence on the conative variable willingness to cross-buy (for lifestyle products, financial services and spare parts) is  also positive (∆ between +0.164 and +0.379, average  ∆ =  +0.248). An influence on brand satisfaction and purchase intention (for both product and repair Services) was not observable as can be seen from the p-values. Highest mean value differences were seen in willingness to cross-buy for lifestyle products (∆ = 0,379) and brand loyalty (∆ = 0,316).

These two KPI's

The results show that being a member of a Facebook fan page has a strong influence on both affective and conative variables. Non-members show lower brand attitude and buying intention than members do. Membership as a key performance indicator can thus be used to assess intended buying behavior (conative component) and emotional affinity of customers to the brand (affective component).


Interaction has an influence on the affective dependent variables as well as partly on willingness to cross-buy. But while membership has an influence on all dependent variables, an influence of interaction on purchase intention and brand satisfaction was not observable. Interaction lacks a significant influence on the conative dependent variables. It can be assumed that interacting with a Facebook fan page does not influence such variables like purchase intention and brand satisfaction since there are other factors playing a more important role in buying a car or being satisfied with it. In the case of brand satisfaction, it is likely that whether a  customer is satisfied with the brand or not depends on the  performance  of the  brand  and not necessarily by how he interacts with the fan page. If the brand performs above the customer's expectation then brand satisfaction will follow. Interaction as a key performance indicator can thus only be used to assess emotional closeness to the brand BMW but not intended buying behavior of members.
The findings of this survey also show that membership and interaction do have a strong influence on brand admirers. The number of members of a fan page and the level of their interaction can therefore be considered as key performance indicators which actually have an economic value for the company using them. The findings also have implications for companies wanting to use a fan page on Facebook. Companies need to implement and monitor these two KPIs in order to evaluate whether their efforts on Facebook are successful or not. This means that companies need to follow these two KPIs closely when conducting a marketing campaign on Facebook in order to evaluate whether said campaign was successful or not. Companies should also focus on acquiring new members for their fan pages since it has been shown that membership has an impact on brand attitude and buying behavior.

Wednesday, August 21, 2013

Facebook Likes and Human Behavior

Earlier in 2013, the Psychometrics Centre of the University of Cambridge conducted an impressive research about how private attributes are predictable from digital records of human behavior, like Facebook likes. Digitally mediated behaviors like Facebook likes can easily be recorded and analyzed, fueling the emergence of computational social science and new services such as personalized search engines and targeted online marketing. However, the widespread availability of extensive records of individual behavior, together with the desire to learn more about customers and citizens, presents serious challenges related to privacy and data ownership. 

The researchers (Kosinski, Stinwell & Graepel) showed that easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of highly sensitive personal attributes including sexual orientation,ethnicity, religious and political views, personality traits, intelligence, happiness, use of addictive substances, parental separation, age, and gender. The analysis presented is based on a dataset of over 58,000 volunteers who provided their Facebook Likes, detailed demographic profiles, and the results of several psychometric tests. The proposed model uses dimensionality reduction for preprocessing the Likes data, which are then entered into linear regression to predict individual psychodemographic profiles from Likes. The model correctly discriminates between homosexual and heterosexual men in 88% of cases, African Americans and Caucasian Americans in 95% of cases, and between Democrat and Republican in 85% of cases.


Predicting individual traits and attributes based on various cues, such as samples of written text, answers to a psychometric test, or the appearance of spaces people inhabit, has a long history. Human migration to digital environment renders it possible to base such predictions on digital records of human behavior. It has been shown that age, gender, occupation, education level and even personality can be predicted from people’s Web site browsing logs. Similarly, it has been shown that personality can be predicted based on the contents of personal web sites, music collections, properties of Facebook or Twitter profiles such as the number of friends or the density of friendship networks, or language used by their users. Furthermore, location within a friendship network at Facebook was shown to be predictive of sexual orientation.


The research 



The Psychometrics Centre, University of Cambridge

The study was based on a sample of 58,466 volunteers from the United States, obtained through the my Personality Facebook application, which included their Facebook profile information, a list of their Likes (n = 170 Likes per person on average), psychometric test scores, and survey information. Users and their Likes were represented as a sparse user–Like matrix, the entries of which were set to 1 if there existed an association between a user and a Like and 0 otherwise. The dimensionility of the user–Like matrix was reduced using singular-value decomposition (SVD). 

Numeric variables such as age or intelligence were predicted using a linear regression model, whereas dichotomous variables such as gender or sexual orientation were predicted using logistic regression. In both cases,the researchers applied 10-fold cross-validation and used the k =100 top SVD components. For sexual orientation, parents’ relationship status, and drug consumption only k = 30 top SVD components were used because of the smaller number of users for which this information was available.

Prediction of Dichotomous Variables

The Psychometrics Centre, University of Cambridge
The aforementioned figure shows the prediction accuracy of dichotomous variables expressed in terms of the area under the receiver-operating characteristic curve (AUC), which is equivalent to the probability of correctly classifying two randomly selected users one from each class (e.g., male and female). The highest accuracy was achieved for ethnic origin and gender. African Americans and Caucasian Americans were correctly classified in 95% of cases, and males and females were correctly classified in 93% of cases, suggesting that patterns of online behavior as expressed by Likes significantly differ between those groups allowing for nearly perfect classification. Christians and Muslims were correctly classified in 82% of cases, and similar results were achieved for Democrats and Republicans (85%). Sexual orientation was easier to distinguish among males (88%) than females (75%), which may suggest a wider behavioral divide (as observed from online behavior) between hetero and homosexual males.
Good prediction accuracy was achieved for relationship status and substance use (between 65% and 73%). The relatively lower accuracy for relationship status may be explained by its temporal variability compared with other dichotomous variables (e.g., gender or sexual orientation).

Predictive Power of Likes


Individual traits and attributes can be predicted to a high degree of accuracy based on records of users’ Likes. The best predictors of high intelligence include “Thunderstorms,” “The Colbert Report,” “Science,” and “Curly Fries,” whereas low intelligence was indicated by “Sephora,” “I Love Being A Mom,” “Harley Davidson,” and “Lady Antebellum.” Good predictors of male homosexuality included “No H8 Campaign,” “Mac Cosmetics,” and “Wicked The Musical,” whereas strong predictors of male heterosexuality included “Wu-Tang Clan,” “Shaq,” and “Being Confused After Waking Up From Naps.” 



Accuracy of selected predictions as a function of the number of available Likes. Accuracy is expressed as AUC (gender) and Pearson’s correlation coefficient (age and openness). About 50% of users in this sample had at least 100 Likes and about 20% had at least 250 Likes. Note, that for gender (dichotomous variable) the random guessing baseline corresponds to an AUC = 0.50. The Psychometrics Centre, University of Cambridge.


Moreover, note that few users were associated with Likes explicitly revealing their attributes. For example, less than 5% of users labeled as gay were connected with explicitly gay groups, such as No H8 Campaign, “Being Gay,” “Gay Marriage,” “I love Being Gay,” “We Didn’t Choose To Be Gay We Were Chosen.” Consequently, predictions rely on less informative but more popular Likes, such as “Britney Spears” or “Desperate Housewives” (both moderately indicative of being gay).

Conclusions


Similarity between Facebook Likes and other widespread kinds of digital records, such as browsing histories, search queries, or purchase histories suggests that the potential to reveal users’ attributes is unlikely to be limited to Likes. Moreover, the wide variety of attributes predicted in this study indicates that, given appropriate training data, it may be possible to reveal other attributes as well.

Predicting users’ individual attributes and preferences can be used to improve numerous products and services. For instance, digital systems and devices (such as online stores or cars) could be designed to adjust their behavior to best fit each user’s inferred profile. Also, the relevance of marketing and product recommendations could be improved by adding psychological dimensions to current user models. For example, online insurance advertisements might emphasize security when facing emotionally unstable (neurotic) users but stress potential threats when dealing with emotionally stable ones. 



Moreover, digital records of behavior may provide a convenient and reliable way to measure psychological traits. Automated assessment based on large samples of behavior may not only be more accurate and less prone to cheating and misrepresentation but may also permit assessment across time to detect trends. Moreover, inference based on observations of digitally recorded behavior may open new doors for research in human psychology.


On the other hand, the predictability of individual attributes from digital records of behavior may have considerable negative implications, because it can easily be applied to large numbers of people without obtaining their individual consent and without them noticing. Commercial companies, governmental institutions, or even one’s Facebook friends could use software to infer attributes such as intelligence, sexual orientation, or political views that an individual may not have intended to share. One can imagine situations in which such predictions, even if incorrect, could pose a threat to an individual’s well-being, freedom, or even life. Importantly, given the ever-increasing amount of digital traces people leave behind, it becomes difficult for individuals to control which of their attributes are being revealed.


There is a risk that the growing awareness of digital exposure may negatively affect people’s experience of digital technologies, decrease their trust in online services, or even completely deter them from using digital technology. It is our hope, however, that the trust and goodwill among parties interacting in the digital environment can be maintained by providing users with transparency and control over their information, leading to an individually controlled balance between the promises and perils of the Digital Age.