Category: Advertising

Know when to play the AI card in eye tracking

Posted on by Dina

By Milica Kovac, New Business Development Manager at EyeSee, Researcher and former Senior Product Manager

Facing high inflation, most decision makers in market research are trying to find alternatives for quick savings. For example, AI-based visual prediction models promise to eliminate the need for eye-trackers as they give faster and more affordable results; and supposedly – just as good.

Let’s examine if this is really the case.

BTS of human gaze analyses  

While both AI predictive algorithms and eye trackers seek to provide human gaze estimations and help us understand attention and visibility KPIs, they operate fundamentally differently.

Regular eye trackers rely on the data obtained from mapping the respondents’ eye gaze, while saliency-based AI solutions predict behavior based on the audio-visual features of the stimuli gazed at, relying on insights from cognitive science – what we know about how humans usually perceive things. In essence, this means that regular eye trackers deliver an answer to what is seen, while AI models suggest what is probable to be seen.

Consequently, eye trackers can chart the variance in behavior of different target groups inspecting stimuli, while prediction algorithms showcase the probability of what is seen by an average human. This means that if your study is looking at an average population, or you are looking for a simple reality check of early development concepts – AI might be good enough for the job. For all other cases, validation or full application of eye trackers is still advised.

Scientific and practical gaps

When talking to an AI vendor, it’s important to ask about the timeframe for which their model predicts visibility. Does it predict what’s most likely to be seen on a product packaging or a webpage at first glance, or does it predict visibility after the user has browsed for some time? You may be surprised by the variety of answers aka absence of any standard in the AI field, as well as by the inconsistency of some models with what we know from cognitive psychology about human memory.

Some AI solutions predict intuitive attention and visibility in the first 150 – 250ms. According to the Atkinson-Shiffrin memory model, when we see something, the entire information registered by our eyes is first stored in our sensory memory. This is a very short-term storage that only lasts for about 250 milliseconds, during which time the information is not yet processed in any way. Only when the information passes into the working memory, under the effect of selective attention, is the limited information about the stimuli being processed but for no longer than 15 seconds (with the average human attention span tending to decrease towards 8 seconds). Eye-tracking devices usually capture attention ranging from 3 to 7 seconds, coinciding with the duration of information processing. Going beyond theory, even from a practical perspective, is it really useful to know what can be observed on a website within a duration of 150-250 milliseconds?

Saliency is (still) mostly context-unaware

To fully understand the power and limits of the AI approach, my team recently completed a validation study of saliency-based algorithm for predictive eye tracking. We selected a number of stimuli typically tested in consumer research studies across industries and channels: from vertical and horizontal packaging stimuli to shelf images and webpages. We compared the results obtained by two different AI models available and popular on the research market with the results obtained using eye-trackers on human respondents.   

What we’ve found is that saliency models are consistently under-predicting semantically important image regions; in some cases, they failed to catch the importance of a brand name on a pack aka failed to determine that those are not just any letters written in certain color, font and size.

What’s more, different models tend to favor different properties such as text, colors, faces, and others. Knowing that helps identify a model’s deficiency and choose an appropriate model for a specific application. For example, some models are better at capturing text area, while in some others, the sound is not considered. Further, different algorithms might not be trained on a certain type of stimuli, which could undermine findings for an entire category.

While this might get better with time, the overall conclusion is that more complex (full shelves, e-commerce websites) and dynamic (video ads) stimuli prove to be way too challenging for AI predictive algorithms as they are still incapable of contextual interpretation. They inspect the size and contrast, not the content; and in doing so, they often fail to capture the meaning. Knowing just how much meaning we attach to brands, letting AI conclude that it is looking at a purple cow feels stripped of all the meaning we attach to a brand like Milka.

An excerpt from a recent study published by the Institute of Electrical and Electronics Engineers provides an additional point of comparison between prediction algorithms and real eye-tracking.

Three different algorithms were used to predict what humans would look at while watching soccer players in colorful jerseys practicing with a football. The first algorithm picked up the colored regions as the most significant points, while the other two algorithms were concentrating on the players’ faces. Both underlying assumptions are justified from a cognitive science point of view: colors (especially red), and faces do grab people’s attention. However, true eye-tracking data showed that people were looking at the ball during soccer match, because they understand the meaning behind this game.

Conclusion

So, what’s the verdict on AI in this case? We’ve previously established that not all AI predictive models are created equal; they process and favor different properties. Keep this in mind, when selecting for a solution – you might find yourself short of one single perfect algorithm; in reality, you’ll have to choose every time you conduct a study.

However, this does not erase the fact that predictive algorithms are more scalable than full eye trackers. It is possible to imagine a scenario where a single application gathers data about both the user and the stimuli. By leveraging the complementary nature of subjective human eye-tracking and objective graph-based visual saliency modelling data, such solution would ultimately lead to a more reliable and efficient output. Until then – real eye tracking is still supreme when faced with complex questions that require nuanced insights.

Interested in application of behavioral methods? Check out our previous blog on measuring attention!

    One team, ten perspectives in 2023

    Posted on by Dina

    2023 is around the corner and the pressure is tangible: so, how do you best adjust for the recession? While predicting the future is never an easy task, we’re firm believers that there’s no better way to brace yourself than to turn to behavioral know-how. Some of our top experts across departments and regions gathered to share:

    • Insights, trends, and opportunities in shifting consumer behavior
    • How to prioritize initiatives and what to avoid as a competitive brand 
    • Ways the MR industry is adapting to be more predictive and meet the needs of clients

    We hope these perspectives serve as an inspiration to think beyond obvious challenges.

    1. Drive actions with insight, not fear

    During a crisis, when trends form and change much faster than usual, it is even more critical to both measure and launch new products that fit the needs of the consumer. With a steeper trend growth, it is essential to try harder to understand the current trends as the client’s needs are also developing faster. This means that the delta between the client’s requirement and the product offering is becoming even more significant – thus, the chance of switching brands grows higher if these needs are not fulfilled. Highly volatile environments (such as the recession) have much steeper trend curves – when that is taking place, it is imperative to monitor them with more research rather than stepping back until things settle.

    2. Get to know the new kid on the block: 2023 Consumer

    All the new pressures of this crisis have led to similar challenges brands had to make two years ago – shortages, supply chain issues, and, consequently, prioritization of product distribution. Due to this, brands had to make complex decisions in terms of trimming their portfolio, reducing pack sizes and counts, or shifting pricing at the same time. Relying on past data is simply not an option now when pricing sensitivity is fluctuating and consumer confidence is unstable. Although previous experiences with different recession periods showed us the various consumer reactions across categories – it is brands’ reactions and choices that are also changing the market landscape.

    3. Avert switching through quality and exclusivity

    Even when high inflationary pressures do not affect the everyday life of consumers, the biggest challenge brands must deal with is remaining competitive – especially with the growing penetration of private label brands. With the appealing prices combined with the on-par quality of shopper-favorite products, private label packs have been making their way into consumer carts more and more over the last years.

    4. Consumers seek to treat themselves under pressure

    But, do consumers recognize your product as indulging? Your pack and claims need to be tested on their shelf performance as 9 out of 10 packs are ineffective and don’t produce sales impact.

    5. Blur the lines between online and brick-to-mortar

    As gas prices reach record highs, so do the concerns about the cost of daily lives. The complex global environment is bound to have major effects on established shopping practices and the functions of touchpoints.

    6. Tune your omnichannel voice 

    A smooth and seamless experience across touchpoints is now fully expected by consumers. Their standards are changing – and brands must keep in mind the hyper-sensitivity of their customers. Research shows that brand loyalties are the first to go as we adjust to the mounting pressures of the global recession.

    7. Ride the wave of cashless payment and delivery alternatives

    Driving value and meaningful connections across the Customer Experience is the top priority for many brands going into every new year – but what to expect in 2023? The key challenge will be finding just the right balance between the overall (and optimized) consumer journey and areas where you should step up on personalization to really bring that added value home. The truth is that the perception of what is valuable goes beyond price and is massively influenced by context; therefore, rethink and treat all in-store touchpoints as an opportunity.

    8. Use videos… responsibly  

    Further, a clear-cut way to gain these learnings is by testing the video content in the right environment – be it YouTube, Meta, TikTok or any other platform.

    Tools such as simulated social media feeds allow complete control over the testing environment and allow you to get more in-depth data on both engagement and brand impact. 

    9. Rethink research processes and data collection

    The MR industry has massively transformed over the last 10-20 years in a way that alternatives are available at every turn – our team, for example, always finds ways to mix and match new methods and frameworks to meet the research questions and challenges.

    10. Team up in crisis

    The journey of successful co-branding begins with understanding the intersection of consumers and their behaviors. Pre-testing your advertising materials (online videos, TVC, social media posts, etc.) and packs can give you crucial insight into how consumers will see, react, evaluate, and if they would ultimately be inspired to purchase your co-branded product.

    A mixed-method approach, where behavioral methods of eye tracking, facial coding and virtual shopping are combined with surveys, can measure such preferences with as much as an 80% correlation with actual shopping behavior.

    Interested in more resources to help you navigate 2023? We’ve got you! Check out this selection of 10 recent behavioral studies.

      Let’s not sugarcoat it: Here’s how to make placement and promotions work in a restricted market  

      Posted on by Dina

      Amongst the many disruptors the markets across the world have felt over the last few years, the UK government introduced new measures on food High in Fat, Salt, and Sugar (HFSS food) – putting in place restrictions and rules on the placement and promotion in both in-store and online ‘impulse’ locations. 

      What will this change for FMCG brands going forward? And more importantly, how can you not only prepare for but operate within this shift? To help brands brace and adapt to the various adjustments in their business, we tackled how brands can:  

      Purchase trigger points can be in unexpected places

      In an effort to fight unhealthy dietary habits, HFSS food has been restricted from aisle ends, store entrances, and checkouts in brick and mortar across the UK. While these locations may be prominent – they are not the end-all-be-all for product placement. Since 80% of shopper purchase decisions are made subconsciously, understanding their decision-making process is an intricate science. Placing items in highly visible areas to trigger that impulse urge was the obvious go-to – but what can your brand do now when these trusty locations are no longer an option? 

       For one, have more faith (but also reliable insights) in shoppers’ intuition and logic – employ a flexible and agile research approach that allows you to test in virtual yet realistic shopping environments. Then, by leveraging them, you can map out the entire consumer decision-making process and the locations shoppers naturally gravitate toward to find your category/product with Behavioral Decision Trees.  

      They pinpoint the reasons behind particular product selections, behavior switches, trade-offs, and sources of loyalty, all while evaluating the overall shopping experiences – and ultimately help you understand how to assist their journey in the changed store landscape. The same Decision Tree tech can be used for testing in digital environments by recreating e-commerce shopping platforms and assessing the online consumer journey – as the placement restrictions will also apply to online equivalents of in-store spots and anything from entry and payment pages, landing pages for other categories, shopping baskets, and pop-ups will be off-limits for HFSS food products. Ultimately, by using Decision trees that leverage virtual shopping, you boost the chances of not missing out on the crucial triggers and touchpoints by 40%. 

      It’s time to go beyond product-based advertising 

      Come January, further restrictions will be in force – bans for HFSS food advertising on TV and restrictions on paid-for online advertising before a 9pm watershed. The advertising landscape is already highly competitive, especially in the social media domain, as we know that consumers scroll through their feeds at the rapid speed of 1-3 posts per second. So, a change like this means that marketers now have to consider a different approach to creating campaigns – perhaps indicating that re-adjusting the focus on the brand itself instead of the product and translating it into engaging ads is one such strategy.  

      Past data taught us that one of the most effective ways to boost purchase intent is to show both brand and product in an ad – so, making the transition to reduce or put a halt on product-centric marketing seems tricky if not executed correctly. A safe way to make sure consumers still resonate with your social media ads and TV commercials and opt for your products (even without showing them) is to test them in a controlled environment that feels as close to the real thing as possible.  

      With a proprietary testing solution and research methods, we have replicated feeds of all major social media platforms to test any ad type and format in the space it would naturally be seen in – and tap into the actual performance and sales potential.  

      Methods like Facial Coding are 2x better at predicting the viral potential of videos than any combination of survey questions – enabling a full-scope understanding of what works and what doesn’t, what can be tweaked and what about your brand grasps viewers’ attention – which in turn, will help you gain a competitive edge and fuel further differentiation between your brand and others.   

      For some categories, HFSS bans are a game-changer 

      While HFSS bans impose challenges on many categories and brands, we have seen that they simultaneously open up new possibilities for others. For example, when it comes to the store environments, the once HFSS-designated in-store spots and displays have now been filling up with other products like alcoholic beverages, cleaning products, and soft drinks.  

      Then there are brands like PepsiCo’s Quaker Oats, Pringles, and Mondelēz International, who saw this as an opportunity to embrace innovation and create a new and HFSS-compliant range of products that would still satisfy the same consumer need as its HFSS predecessors. 

      Inflation has already caused major shifts in how consumers choose to spend their money –  and even without the new restrictions, many brands have embraced new product development and opted to rethink their portfolios. However, as a rule, innovation can be risky (more than +80% of new products fail), but volumetrics and market share projection can empower your NPD process by estimating the success of any new product launch. In fact, there are a few levels of studies that utilize the virtual shopping solution (that shares a 0.8 correlation with real shopping behavior) and behavioral methods to ensure the risk of an unsuccessful launch is significantly minimized by: 

      • Screening product concepts to identify the most promising ones  
      • Gaining the learnings to optimize the concepts for further development
      • Validating the optimal concepts and evaluating their future sales potential  

      Summary

      As with any change that comes, there are those who embrace it and adapt – and those who fall short. The HFSS restrictions in the UK are no different – they present a sea of opportunities and possibilities to rethink and develop innovation and rekindle the relationship with your consumers for those who are interested in winning.  

      Relying on a behavioral research approach to guide you during these transforming times will equip you with the predictive learnings needed to make these sound decisions – and reduce the risks that come with the inevitable shifts in the market.  

        One approach: Ten studies that pushed the boundaries of consumer research

        Posted on by EyeSee Research

        EyeSee is turning 10 this year! To celebrate this decade of insights, innovation, and studies that pushed us forward – we have collected and hand-picked our most memorable studies and learnings over the years. From projects with clients like Twitter and Smurfit Kappa to self-funded studies tackling topics we knew were worth exploring – strap in for an insightful journey ahead as we look back at the 10 behavioral projects that helped us grow, expand our knowledge and tech and ultimately transform the approach to traditional consumer research:

        1. Getting sustainable products just right

        86% of consumers want to go more eco-friendly – so what’s stopping them? In this study, we set out to understand how brands could support their consumers by developing powerful communication and product claims and identifying categories that lack ‘greener’ alternatives – with quite a complex behavioral framework. The comprehensive undertaking included an in-depth look into who the green buyers are, which claims are most appropriate for use on product packs, and what makes an impactful kind of social media posts work best to inspire eco behavior and more!

        2. The price of consumer confidence under inflationary pressures

        With the transforming global and economic climate came shaken consumer confidence – and the high price points on the store shelves are palpable to both shoppers and marketers. The previous experiences with recession periods showcased that shoppers react differently across categories and markets making it clear that it is vital to feeling the consumer pulse in the changing setting. So to help brands operate in it, we turned towards understanding the current shopper behavior and assessing the best strategies to cope with ongoing inflation for both CPG and retailers – like, when do consumers opt to stay loyal to the brand and when do they switch to the alternatives?

        3. A tree is best known by its consumer decisions

        Do you know how shoppers decide which product ends up in their cart? We wanted to know too! So to do that, a behavioral component was added to well-known research tools: decision trees. This led to a complex meta-analysis on over 35000 respondents from dozens of projects across FMCG industries – which also included a comparison of survey results and virtual shopping data to determine just how unreliable surveys can be in mapping out consumer decision-making. Learn just how different behavioral decision trees are different to standard studies, what it takes to extract the biggest ROI from decision tree research and who benefits the most from these studies – and why trusting what consumers say is much more dangerous than you might think!

        4. Hitting the mark on socially conscious advertising

        Great social media content has the power to trigger a reaction in under 2.8 seconds and significantly impact brand perception. Yet when it comes to socially conscious advertising – getting the right tone and message can be a hit or, more often than not, a miss. So, our best researchers turned to behavioral insights to uncover just how crisis messaging should be done and how it affects brand equity. Check out the results of one of the most extensive mobile behavioral studies that was conducted on 1800 respondents in a simulated Instagram environment and learn how to nail your brand’s communication while tackling highly important social topics.

        5. Driving sales with in-store display optimization practices

        Just how powerful are point-of-sales displays in the store? Well, they can boost sales by as much as 20% when done right. We joined forces with Smurfit Kappa to pinpoint what drives in-store visibility, attention, likability and share of shoppers – by testing more than 400 POS materials on +60,000 shoppers across 15 countries worldwide. As it turns out, the best-performing display is 4 times more visible and could increase purchases 7 times more efficiently than the worst-performing ones. So, if you are developing in-store material that needs catch the attention in a crowded supermarket – these best practices are for you!

        6. The secret behavioral sauce of successful innovation

        Every brand knows the staggering statistic that over 90% of new products and innovations fail when launched – but the pressure to continue the development never ceases. To empower brands in their innovation endeavors, our team of researchers sought to showcase what a Market share estimation study looks like. What the study on introducing and measuring the success of a new product aimed to do was verify how the behavioral NPD solution fares against real-life sales data. If you have new products in your pipeline, this study is a must-read as it covers:

        • How to leverage the latest behavioral tech to ensure a successful new product launch
        • The new product opportunities to tap into in both brick and mortar and across digital platforms
        • All the crucial steps brands should take when going into innovation development

        7. From in-context testing to winning social media ads

        As news around Meta, TikTok and now Twitter continues to take the headlines by storm, the already tumultuous space of social media, where users scroll at a speed of 1-3 posts per second, has raised new concerns for advertisers and marketers. But, some social media best practices are evergreen. And so we have compiled a data-driven guide for making sure your ads are worth the investment and more importantly, captivating for the viewers. Since there are so many different things to have in mind when starting to test your social media ads, we have also included the most impactful things you should focus on from the start and which ones you can include if your budget allows it!

        8. The precious 6-second ads w/ Twitter

        Social media feeds are one of the hardest clutters for brands to break through – especially with the ever-growing percentage of mobile users. With this challenge in mind, we teamed up with Twitter to determine the optimal ad-viewing length by replicating Twitter feeds and studying user behavior in a controlled environment with reliable behavioral methods. The learnings were game-changing and led to Twitter introducing the 6-second biddable video ads on their platform! The study uncovered that these short-form and branded videos, with the sound turned off, have a much stronger ad recall on mobile than traditional TV commercials we are used to seeing – revolutionizing the way advertisers approach social media ads.

        9. Wrap it up with some holiday insights

        How will inflation impact this holiday season? Regardless of the current sentiment, many are expecting growth in sales numbers. And from festive advertising to online and store touchpoints, there are plenty of opportunities to get shoppers into the holiday purchasing spirit! We compiled our best behavioral learnings (did you know that using logos in festive ads boasts a 133% higher brand recall?) from multiple advertising, shopper and digital studies with a goal to help prepare your strategies for 2023 – cause we know that omnichannel optimization and a seamless cross-channel experience is something that is vital for success with shoppers all year round!

        10. Twitter’s look into the powerful role of gender in sports ads

        How does gender portrayal in (sports) ads impact the performance of the creative? To uncover what it means for brands to tap into uncharted territories with their advertising, we once again joined forces Twitter and explored the impact of gender representation in sports ads – and found some unexpected results, such as:

        • Women are taking the lead – both traditional and non-traditional gender roles in ads outperform their male counterparts
        • Ads with male athletes just don’t do the trick anymore! They’re less credible and empowering – men are looking for more relatable role models
        • Cultural relevance is crucial to a consumer’s purchase decision and correlates with performance on brand effect metrics


          Behavioral insights: Backbone of successful co-branding initiatives

          Posted on by EyeSee Research

          Written by Jason Bradbury, Sr. Director of Client Service at EyeSee

          I am a simple individual and perhaps a creature of habit – choosing peanut M&Ms as my go-to sweet snack, relying on Cinnabon k-cups for my daily coffee fix and letting Apple technology keep me well-organized and connected.

          While data (and life) confirm I am not a lone example of a consumer having favorite brands, recent research shows that these loyalties are first to go as we adjust to the mounting pressures of the global recession. Apart from tinkering with variables of pricing and volume, there are other strategies your brand might explore to preempt eroding loyalty.

          In fact, there’s a good chance one of your new favorite products may just be the result of two separate brands working together – the fruit of a co-branding or licensed partnership initiative. If your goals for 2023 include:

          • Reconnecting with or Expanding your consumer base;
          • Evolving your brand identity or reputation;
          • Innovating the product;
          • And/or all the above…

          …then co-branding may be the right strategy for you! However, this approach does carry certain risks and mitigating them should be a top priority. Here’s how behavioral research can help.  

          Know your shifting consumer and (re-frame) their needs

          75% of brands could disappear tomorrow … and most consumers wouldn’t care. On top of this, shoppers are already actively engaging in brand-switching behavior due to rising inflation. By exploring collaborations within or across categories, you are opening a whole world of possibilities to either deepen the connection with existing consumers or to expand your base.  

          Well-known consumer products entering into a partnership with Disney is one such example.   Disney-licensed characters are displayed on Huggies diapers, Band-Aid adhesive bandages and even Gucci collections! Disney characters are iconic, instantly recognizable, and intergenerational.  Through these collaborations, these brands have managed to overcome their challenges in creating appeal and eliciting an emotional response, which has an enduring effect on retaining brand loyalty but also helps draw consideration among new potential customers.

          The journey of successful co-branding begins with understanding the intersection of consumers and their behaviors. Pre-testing your advertising materials (online videos, TVC, social media posts, etc.) and packs can give you crucial insight into how consumers will see, react, evaluate, and if they would ultimately be inspired to purchase your co-branded product. A mixed-method approach, where behavioral methods of eye tracking, facial coding and virtual shopping are combined with surveys, can measure such preferences with as much as an 80% correlation with actual shopping behavior.

          Introduce agile reality-checks to your co-branding initiative

          On average, less than 20% of product and pack innovations prove to be a success. Adopting an iterative approach and testing at each step of development increases the chances of yielding a positive result.

          More specifically, there are 3 main points where behavioral research can play a big part in shaping your co-branding initiative:

          • Screening: start testing early in the process (even concepts and drafts!) and narrow down your options. Leverage more granular sub-category criteria, including usage frequency, understanding brand awareness and openness to purchasing the product, and even filtering on geolocation. With every added testing criterion, the potential risk of a new launch gets smaller.
          • Test in context: use virtual simulations of stores and retail environments to tap into authentic consumer behavior with high accuracy. The same goes for e-commerce – any website or webpage, such as Amazon, Target, Kroger can be replicated. Having the ability and agility to put respondents in a context that feels familiar and authentic is key in estimating the success of the co-branding strategy.
          • Volumetric and Market share projection: test claims, pricing, and other aspects of launch to estimate in-market success, switching behavior and opportunities for driving share within the first year.

          Make co-branding resonate: Optimize at every touchpoint

          Experts concur that having a seamless and experience-driven path to purchase is more important now than ever. Shoppers’ expectations are changing – and brands must be aware of the hyper-sensitivity of their customers. Thus, co-branding can be an effective tool to not only enhance brand or product communication, but could also serve as a potential visual cue for highlighting variety or sub-line differences.

          Additionally, there are many widely overlooked opportunities within omnichannel – optimizing touch points such as e-commerce pack shots being one of them. Hero images can significantly boost sales by attracting more attention. They garner 5% higher visibility than Standard Package Designs on desktop (with even greater potential on mobile because of the smaller screen size) and can increase sales by about 15%. Considering these key touchpoints when implementing a co-branding strategy can significantly boost your chances of success.

          Summary

          Co-branding is all about expanding opportunities to connect viscerally with the consumer. By introducing new propositions and potentially enhancing communication by leveraging the established equities of each brand, you are generating broader interest and/or emotional response, which has a positive effect on consumer retention.

          Adopting behavioral methods and testing within contextual shopping environments allows more authentic and predictive insight into how your co-branded product will perform. This type of feedback minimizes the risk of unfruitful investment and represents a definite advantage – even more so under the pressures of recession, where consumers are increasingly fickle and marketing budgets precious.

            Capture their attention first, and the ‘heart’ next: attention & emotions in social media advertising

            Posted on by EyeSee Research

            Written by Vanja Radic, Facial Coding Team Lead at EyeSee.

            Many of our clients have asked what a successful social media campaign entails. In this article, we will address the most important creative aspects to have in mind when directing and optimizing social media ads. Those aspects revolve around two main pillars: attention management and emotional engagement.

            TVC vs. social media

            Although attention metrics can always provide additional insights, they are not essential when it comes to TVC testing; as for this advertising format, some amount of attention comes as a given – the TV is on, and we just move on to other activities until the TVC clutter dissipates. A lower level of attention is even considered a unique TVC advantage, allowing a more subliminal persuasion to take place (Heath, Robert). Countless academic discussions address the pros and cons of TVCs vs. social media advertising, however, when it comes to a younger and more specific target audience, social media marketing is without a doubt winning the game. Nevertheless, social media as an environment poses additional challenges when it comes to creating a successful video ad. Ferociously fast-moving timelines have brought on the need for marketers to become excellent managers of attention. Consequently, attention metrics come into play as the strongest indicator of success: being three times more predictive than viewability, attention metrics inform marketers about how much of the video content will actually be seen.

            Let’s introduce an analogy: the difference between seeing a movie cover and seeing the whole movie or a part of it aptly illustrates the difference between viewability and attention. Unfortunately, most social media analytics limit themselves to viewability, in that way stunting the learnings from past campaigns.

            Yet, it’s important to note that testing an ad only on attention metrics doesn’t give a full picture of its performance and therefore limits the feedback on where the spaces for improvement lies. Attention metrics represent only one side of the coin since they say nothing about a very important driver of attention and consumer behavior overall – emotions.

            Attention vs. emotions

            It’s difficult to talk about attention without appreciating emotions since they can critically modulate attentional processes and, at the same time, increase the likelihood that an emotional experience becomes part of our memory store; in turn, creating an emotional connection to the brand.

            “A marketing strategy focused on appealing to consumers’ raw and most personal emotions can change a faceless, perhaps seemingly soulless, business into a brand that audiences can relate to and care about.” (Ingwer, Mark)

            We are constantly bombarded by a plethora of information and experiences, only a small subset of which will be encoded into lasting memories. That small subset that is likely to be selected from the barrage of information is the emotional content. Apart from transforming experience into a memory, emotions powerfully, predictably, and pervasively influence our decision-making, which is why brands should make sure their advertising efforts elicit positive emotions.

            The best way to access the emotional quality of an ad is by applying the Facial Coding method. As both appealing to emotions and managing attention are equally important, EyeSee’s methodology relies on both facial coding and attention measurement when assessing an ad’s performance on social media.

            How we do it

            Nothing better than an example to illustrate the complementarity and uniqueness of these two methods. Here are the results from a YT ad testing study, summarized in Retention rate per second (Attention) and Emotional engagement per second (Facial Coding) graphics. 

            A look at attention measurements for this ad shows that the retention rate drops below the benchmark from the moment the skip button appears. This drop severely influences other attention metrics, like competition rate and overall focus, as the viewers who click the skip button are irreversibly gone (the line can only go down). Still, we can see that there is a shift in the 7th second, where the line starts to straighten, from that moment on, floating above the benchmark. 

            Graph 1 – Retention rate per second (Attention)

            Now let’s consult the emotional metrics provided by Facial Coding:

            Graph 2 – Emotional engagement per second (Facial Coding)

            From the standpoint of facial coding, the ad is a high performer, reaching a 20% positive tipping point in the 11th second. Obviously, humorous scenes developing from the 7th second have done their part in positively engaging viewers’ emotions and need no further script-based modifications. If we go back to the Retention rate graphic (Graph 1), we cannot help but notice how emotions interfere with the attentional processes – i.e. attention drop-off decreases from the same moment that stimulus starts to engage the viewers. However, if we were limited to attention measurement metrics only, we might be tempted to wrongly assess this social media ad as an average-to-low performer; nevertheless, Facial Coding demonstrates its strength and potential in engaging positive emotions, hence sharpening the feedback given. Therefore, by combining both attention measurement and facial coding, we can say for certain that the biggest space for improvement lies in the first part of the stimulus; this is probably due to a lack of suspense or dynamic shift around the 5th second, that second being the stumbling stone for effective attention management in the YT environment.

            Insights into social media ad performance can be even more enriched by supporting these two methods with other behavioral methods such as Eye Tracking, Virtual Shopping and Reaction Time Measurement. Given that Facial Coding yields data on how the respondents feel when exposed to an ad, Eye Tracking is utilized to pinpoint what exactly they are looking at when watching the video, uncovering the main areas of interest. And while an ad can be both entertaining and attention-grabbing for consumers, generally excelling from the creative side – the question of what it brings to the brand remains open. That is where Virtual Shopping comes into play, enabling us to measure the actual impact on sales, whereas Reaction Time Measurement ensures we understand the impact on the brand itself.

            Conclusion

            Relying solely on attention metrics in social media testing is not enough if we really want to learn from past experience and squeeze the most out of the input available. By applying the right combination of EyeSee’s behavioral methods, we can understand both the emotional and attention aspects of video content, which allows us to pinpoint exactly where space for improvement lies. 

            If understood and excavated properly, emotions can be powerful commercial tools and many brands have come to the conclusion that appealing not only to consumers’ reason and logic but also to their heartstrings can give them a competitive advantage. Besides establishing attention as an adequately managed KPI, Facial Coding method helps marketers ensure that their advertising efforts are successfully connecting with their audiences emotionally.

            Heath, Robert. (2012). Seducing the subconscious: The psychology of emotional influence in advertising. Wiley-Blackwell.

            Ingwer, Mark. (2012). Empathetic marketing: How to satisfy the 6 core emotional needs of your customers. Palgrave Macmillan.

            Advertising Week: Attention is the New Metric

              The latest in social media testing: Replicated feeds for authentic behavior

              Posted on by EyeSee Research

              The future of shopping is set for a social revolution. Thanks to its accessibility, social media has quickly become one of the essential business operations for brands. And due to the highly competitive digital arena, growing a brand’s social presence has never been more challenging – from standing out in the clutter and ensuring ads actually trigger the conversion into purchases to knowing how to successfully navigate the polarizing timelines caused by turbulent events and crises.

              Check out Laura Hoste (New Business Development Director, EyeSee) give a comprehensive run-down of this innovative research approach to testing social media campaigns:

              What are the current social commerce trends and drivers?

              E-commerce sales have soared in the last years and with that, the way people are shopping has changed fundamentally. And now there is Gen Z – a new consumer group that is completely transforming the face of online shopping. A trend we have seen time and time again since the rise of TikTok is its potential to blow up products to unseen highs of virality and almost permanently clear them from the shelves. The power of social media is immense.

              But these short-format-based apps are certainly impacting our attention spans. In fact, viewers only spend 2.5s per post, according to Facebook. While 2.5s sounds scarce (because it is), the consumer’s attention in actual physical stores is not that much greater – only 7s!

              Of course, researchers and marketers know how precious and hard to obtain attention is in any environment – but the digital arena is way more cutthroat and competitive than anything we’ve seen so far.

              What are the go-to research tools?

              Because of the highly competitive environment, the pressure is on brands to find more innovative data and drive successful campaigns. However, researchers usually take the route of extracting data from live analytics via social media platforms, different social media tools, surveys and focus groups. And while these methods can be handy, they are not without some gaps.

              First off, they are missing the why – why is a certain trend happening, and why are consumers resonating more with this post instead of that one. Then there’s the reputation risk and the opportunity cost of launching a non-tested ad. And, of course, it’s hard to understand if consumers are connecting with your brand – although extremely important when it comes to advertising, tools like live analytics give no insight into which parts of the post or ads are performing well or how they are directly impacting the in-store purchase behavior. And finally, none of these methods can provide strategic insights both across social media channels and other marketing channels such as TVC, digital, print, OOH.

              What is the value of CMS or in-context social media testing?

              CMS stands for content management system, which is a computer software used to manage the creation and modification of digital content. Essentially, it is a platform capable of cloning or rather replicating social media channels and websites.

              By developing a replica of the social media environment, the quality of research insights significantly boosts. And the more realistic the environment, the more predictive and precise understanding of authentic consumer behavior! But this also means that you can have full control over the testing in terms of stimuli, the target group, the entire timeline, and its features. Shortly, the study setup is completely customized to your particular research needs. And with the help of an in-house design team, any major social media platform can be recreated – and in it, any format of an ad or content can be tested and optimized!

              Testing with combined methods yields higher predictive power and maps out specific elements of an ad that work (or don’t work) with the target audience. As a result, you gain a lot more strategic insights that allow you to create guidelines and frameworks for creative agencies and for developing ads that can be tweaked according to the platform. Especially since each one has unique qualities to it and what works on one, let’s say, putting the brand logo in the left corner on Twitter ads might not work on Instagram, where it needs to be in the bottom right. This is why it’s crucial to pre-test and really understand how your content can be additionally tweaked and optimized for every platform. And that is how we designed this CMS solution – to deliver brands a competitive overview of their ads and content performance across different platforms such as TikTok, Instagram, Twitter, YouTube, Snapchat and Facebook – check out the demo!

              How does in-context social media testing work?

              For reliable and valid insights, it is crucial to use a mix of behavioral and traditional methods that focus on consumer behavior in the timeline and its impact on sales uplift. Surveys help uncover the why behind ad performance – beyond just the clicks, views and other analytics, but digging deeper into consumer perception.

              Eye tracking, in particular, allows granularity into which ad elements are seen and which are often missed, while facial coding identifies whether consumers are engaging with your brand by analyzing their emotions through facial expressions. And virtual shopping provides a direct link between the performance of an ad and in-store purchase behavior with the help of realistic simulated store environments that tap into authentic consumer behavior.

              And because of the online and accessible approach, respondents are recruited from anywhere in the world via a third-party panel, allowing studies across different markets, countries and industries. And the best part is that no extra tech is needed – respondents simply use their own laptops or mobile phones during the test.

              What does CMS testing uncover?

              Every metric and KPI you need to know about your ad performance:

              1. Visibility –  how many users have actually seen your content?
              2. Attention – how long do they watch it for?
              3. Video retention – what are the usual points where you start to lose them?
              4. Emotional reach – is the ad resonating with them?
              5. Survey KPIs – does it fit with the brand, and do users like it?
              6. Sales uplift – does the ad impact sales?

              But going beyond these KPIs, it is important to have a holistic view of how the ad performs across different platforms – to gain overarching best practices and guidelines.

              How are simulated feeds the gateway to connecting with consumers?

              Apart from enabling an incredibly nuanced understanding of ad performance, testing content in simulated social media feeds opens opportunities for brands to connect with consumers and explore topics relevant to them. Since this, too, varies from platform to platform, uncovering the sophisticated differences in behavior that would go undetected with traditional social media research tools is crucial! Here are some insights we have accumulated over the years:

              Instagram: In one of the most extensive mobile behavioral studies conducted on 1800 respondents in an Instagram environment that tackled brand perception, we uncovered that IG users tend to prefer full body shots, celebrities & female protagonists – for most industries, that is. Ads featuring Female protagonists drive more positive emotions and are evaluated as more attractive and transparent, and this stands for Endorsement and Seasonal ads in particular. 

              Twitter: Another study done on a Twitter timeline showed that the key to uplifting sales is that combining and showcasing both brand and product significantly increases the purchase intent. Only showing the brand or product does not have the same impact. Furthermore, the findings showed that placing the brand logo in the upper left corner actually boosts recall!

              Facebook: A Facebook study where 26 ads from 6 different industries were tested found that ads from the Food industry were the ones grabbing the most attention – they outperformed other ads on visibility, attention and emotional reach. And – if you can, avoid GIFs! Videos are proven to be far more persuasive, driving both better brand perception and differentiation.

              Interested in optimizing your social media presence? Reach out to us!

                The battle for attention: How to retain consumers’ focus in global crisis

                Posted on by EyeSee Research

                Written by Vanja Radic, Facial Coding Team Lead at EyeSee.

                It’s become a given that attention is the scarcest resource that brands are fighting for. While the cost of attention has been rising rapidly and consistently in the past decades, at the same time, the quality of paid attention has been decreasing at an even greater pace. The ever-so-dynamic digital arena – where conversations around global events and polarizing topics happen constantly and quickly – presents a big challenge for brands to truly grasp and hold viewers’ focus. So, how can brands navigate these rocky waters amid major happenings such as the pandemic or war in Ukraine?

                The truth is that relying only on the number of views is simply not an option anymore. Instead of counting mere views, marketers are now compelled to turn to more attention-oriented metrics to accurately measure their past campaigns’ performance, as well as predict the success of future ones – regardless of the content surrounding them. This is where behavioral methodology comes into play by helping brands uncover how viewers interact with the content in a natural environment.

                The price of attention is high

                According to Facebook, only 2.5 seconds are spent viewing each post from a desktop device and even less on mobile. Moreover, EyeSee’s studies have indicated that only 7% percent of people who view a 30-second video post on a timeline actually see the whole video, while about 27% of viewers stay on the post for less than one second. Relying solely on the data that social media platforms offer can be insufficient since real viewer engagement lies in how long they actually watch the video. In summary, a high budget for an ad creative and its promotion is at risk if the creative fails to grab and retain attention, as quantity doesn’t make up for quality. It comes down to this: you can buy a time frame in a clutter of TVCs, and you can boost your social media ads, but what you cannot do is buy people’s attention – you have to earn it.

                That is why it is essential to understand how viewers interact with content in an environment that’s closest to a natural  one. Here, the behavioral methodology makes all the difference. EyeSee’s attention measurement solution provides an easy way to measure a content’s ability to not only attract, but also retain by offering digestible outputs in the form of simple KPIs that point to spaces for improvement. For example, attention KPIs will provide answers to some of the most commonly asked client questions, such as:

                • Is the content attention-grabbing enough from the very beginning?
                • Is it capable of breaking through the clutter?
                • Are there some bigger drops in attention that indicate room for improvement?
                • Which percentage of viewers will actually watch the whole video?
                • What is attention-grabbing for a particular target group?
                • What are the patterns behind successful attention management?

                A clear-cut way to gain these learnings is by testing the content in the right environment. Tools such as simulated social media feeds allow complete control over the testing environment and the possibility to experiment, as well as provide precise insight into how viewers interact with the content – and more importantly, how it can be optimized.

                It takes seconds to make it or break it

                Timing is everything. There are cases in which a lot can be improved with simple editing. The very same material can deliver a much higher ROI if the most attention-grabbing scenes are placed where they should be as, as we like to call them, stumbling stone seconds. Stumbling stone seconds differ from one environment to another. Whereas you’ve got 5 seconds to earn your viewer’s attention on YouTube, other mediums like Facebook, IG, TikTok, and are less forgiving, demanding from creative to arrest attention from the very first second – fortifying the need to test and optimize for every timeline environment.

                So, what makes a show-stopping video? Here are some top and bottom performers’ common characteristics regarding creative’s two main qualities: 1) its ability to break through the clutter and capture attention (stopping power) and 2) its ability to retain the attention (retention rate):

                One of the most common pitfalls advertisers make is not leveraging the very first seconds of the video. Consumers spend less than 2.5 seconds on a piece of content before they continue to scroll or change the channel, so ensuring they are hooked from the get-go is a must. Applying a dose of mystery is definitely one of the ways to accomplish that since it triggers our compulsion for completion. Novelty, contradiction, and immersive experience are also great means of arresting attention. On the other hand, predictability, one-dimensional and overused scripts, especially when combined with overly prominent branding, tend to lose their viewers’ attention at the very beginning.

                However, when it comes to retaining attention, different rules apply: a creative should be easy to follow, entertaining and dynamic with emotional ups and downs. Confusing and monotonous creatives, as well as those that fail to deliver reward for tension built, tend to lose their viewers along the way.

                The steps to success are build-measure-learn

                The need for effective attention management is higher than ever, and the demand is only bound to get higher. Cutting through the clutter has always been one of the greatest challenges in advertising – and with sensitive news such as the war in Ukraine, elections, or the pandemic in the very same environment as your campaigns – it has become an even greater challenge to stand out in the sea of content. Although posts and conversations around these sensitive topics are not something you as a brand can control, EyeSee’s showed that advertising is still safe in the news feed regardless of its adjacency with controversial content.

                And while there are some standard practices when it comes to arresting users’ attention, the only sure way to properly manage your target audience is by pre-testing your creative content. Even the best tricks, when decoded and widely used, can get worn out. The best way to overcome this challenge and find out what works best for your target group is to utilize the right mix of methods that will help you uncover predictive insights into the content’s performance. Regularly measuring the performance of your its attention metrics in an adequate environment, will provide you with insights into creative’s aspects that require improvement and, more importantly, it will allow you to have a great learning strategy in the quest for understanding what resonates best with your target audience in terms of attention management.

                Interested in optimizing online videos to keep the precious attention of the viewers? Reach out to us at [email protected] 

                  Social media impact: How much does social media content affect actual shopping?

                  Posted on by EyeSee Research

                  Social media campaigns hold a great power to tackle important issues, such as BLM, COVID-19, and the pressing concern on climate change and plastic pollution. Most social media campaigns that address these topics are communicating in such a way that can make consumers feel concerned about their future – but this approach seems to lack the impact on actual consumer purchase.

                  This is the third installment of the study exploring what makes a competitive sustainable product win on the shelf – the first two parts covered which consumers you should be talking to and how to choose just the right product claim that resonates with the green shopper.

                  Part 1: The green horizon: An intro to the green buyer and how to measure eco behavior
                  Part 2: Walk your talk: Strategies for choosing your sustainable product claims wisely
                  Part 3: Social media impact: How much does social media content affect actual shopping?
                  Part 4: Virtual shopping: Why some categories are leaders in change, and how to become one

                  Science sells, but familiar faces pull focus

                  Product marketing is all about emotions – for hundreds of years, marketers’ main goal was to trigger just the right feelings and ensure consumers feel good about the purchases they are making. So, is this the key to encouraging more eco-conscious shopping as well?

                  The study included 4 different simulated Facebook timelines, and each timeline had 4 different posts tackling the same topic of plastic pollution. The categories of the 4 types of posts were – scientific posts, those promoted by mass media, celebrity-endorsed ones, and posts from NGO campaigns.

                  A combination of eye tracking and facial coding methods tracked eye gaze and detected emotional reactions to the posts in every timeline. Each exposure to the timeline was followed by a virtual shopping task and a survey. Although facial coding and eye tracking are vital when testing ads – you need to rely on more than one method. While they can uncover if ads are emotionally captivating – only by combining them with virtual shopping, it becomes clear how well emotions translate into action.

                  The change can be made if you understand the consumer challenges

                  As we mentioned in previous installments, there is a significant lack of awareness that each individual can make an actual contribution – only 34% of shoppers think they personally can contribute to solving the problem of pollution. Interestingly, the findings showed that ad exposure did significantly increase sales of sustainable products by up to 9% (from 9% to 18%) – suggesting that taking time to really educate the consumers and provide facts and data will impact the demand for more eco-friendly alternatives.

                  Important to note here – these results can not be compared to the data collected from testing ads that directly promote a product and are then followed by a shopping task for that exact product. The content that addresses environmental issues has a much more challenging task of not selling anything but still influencing how consumers shop.

                  There is no one-size-fits-all post – you must create a funnel

                  So if some posts perform better in terms of triggering emotions, but others actually influence the shopping behavior – how should brands approach addressing this issue?  In part one of this series, we mapped out the different types of green shoppers and their varying levels of eco-awareness. Understanding the differences and nuances between consumers’ readiness to act green is fundamental for targeting their exact motivations as you craft the messaging of your posts.

                  Here is a handy breakdown of the post performances:

                  To ensure the entire spectrum of the consumers is covered, it is best to build a funnel.  Firstly – evoke interest in the issue. For this, celebrity and NGO ads are very effective – they hold the attention for about 5 seconds on average, compared to the Scientific and Mass Media posts, which were looked at for 3.45s and 3.91s, respectively. On top of this, posts that featured celebrities aroused the most positive emotions and interest! So while great for raising awareness on the issue, the main challenge becomes truly impacting the eco behavior – and this is where scientific types of posts can give that one extra push towards action!

                  The posts with messages that appeal to the viewers’ emotions drive higher emotional reach, likability, clarity, personal relevance, and persuasiveness and are deemed more credible. The data showed that messages striving to evoke fear are seen as less persuasive. So seek to inspire and empathize – not shock!

                  Key recommendations straight from our experts:

                  • Grab attention with powerful visuals or celebrity ambassador – make sure the celebrity spokesperson has credibility and a spotless reputation
                  • Demonstrate expertise – educate your shoppers about pollution and plastic waste issues and showcase what they can do to help
                  • Be honest about your share of responsibility – be transparent about how your brand is contributing to this cause
                  • Make consumers feel good about buying a sustainable alternative – do not try to guilt them into buying because it does not work.

                    [Luxury journey] 3 ways to triumph at customer experience

                    Posted on by EyeSee Research

                    One of the many things the luxury industry excels at is going beyond just the product – but creating exclusive experiences at every touchpoint of the customer journey. Luxury has always been a state of comfort, an intangible feeling of exclusiveness – and as such, not rational. The key challenge for high-end brands lies in capturing that unique and implicit feeling of luxury. How does one go about researching something that is irrational, subconscious and not easily communicated – all while taking into account the pandemic-driven changes in customer demands? Cue behavioral market research to ensure a safe metamorphosis.

                    LVMH has been paving the way for changing the luxury customer experience and the ways we approach enhancing it. As a part of the annual LVMH Innovation awards, EyeSee had the honor of being amongst the 28 finalists dedicated to providing tech-driven solutions and bringing the future of customer experience one step closer.

                    Check out Milica Kovac‘s quick guide to winning big with behavioral insights:

                    Here are 3 ways brands can embrace the evolution of customer experience:

                    Tap into transformative in-store trends

                    The pandemic has pushed a lot of brands across industries into fight or flight mode – some flourished and some failed to adapt to the new dynamic the health crisis has brought on. However, now, as more vaccines are administered every day, buyers have started to go back to the stores after a year-long pause. But just as shopping habits continue to evolve, in-location gadgets, protocols and regimens will have to be reinvented and tested to fit the new needs.

                    One of the ways to keep up with the consumers is by putting them in context, a completely simulated virtual environment of any store, and testing new touchpoints to tap into which store elements work with the consumer – and which ones don’t, beyond the explicit.

                    On top of it, mapping out their entire decision-making process and identifying the type of customer is crucial when it comes to brand loyalty – and luxury is all about loyalty, but having a loyal customer is a luxury. From there on it’s all about how to assist and improve their shopping journey to ensure they stay with your brand and understanding where new buyers come from, and what allures them to your brand.

                    Lean into digital

                    Luxury brands have been on a mission to tap into the digital experience, but most of them have met the same challenge – making it feel exclusive to the consumer. The rise of Gen Z and the perpetuated need for digitalization are disrupting the market and pushing high-end retailers to get innovative. From virtual try-ons, to digital shopping assistants, even the likes of Ralph Lauren and Gucci have invested in the development of digital platforms to unlock a new way of connecting with their customers. So, how can brands engage with luxury e-shoppers and meet their new demands?

                    Over 53% of planned online purchases fail to be completed – consumers tend to get frustrated and give up if there are any setbacks in their online path to purchase. Understanding how to navigate all the steps consumers take (or don’t take) while shopping online will determine the common pitfalls and pain points where you could be losing shoppers – but ultimately the opportunities ahead. To uncover the fine nuances in the ways consumers are interacting with shopping platforms, you must tap into the online path to purchase.

                    Bridge the in-store – online gap

                    The need to tie in both commerce and e-commerce and create a seamless experience across all platforms has been something companies from every industry are trying to achieve. One of the trends that emerged in the Auto Industry, for instance, is the development of virtual showrooms where consumers are able to view and browse vehicles as they would in person – and this trend found its way across many industries.

                    Click-and-collect is becoming a more and more popular choice among buyers, and as Google reports, 63% of shopping begins online. But what’s certain is that consumers still want to experience the immersiveness a physical luxury space can offer – from social interactions to touching and seeing a product. The key to ensuring a smooth omnichannel path to purchase lies in truly understanding the consumer, their expectations and needs – and, perhaps more importantly, their behavior.

                      Thanks for your interest!

                      We”ll get back to you promptly