by Sentimenti Team | Jun 6, 2019 | SentiBrand
Emotywne pozycjonowanie reklam, czyli targetowanie reklam wg emocji od niedawna nabrało nowego wymiaru. Okazało się, że komunikat można oprzeć nie tylko o kontekst, analizę ruchu na stronie, badania demograficzne, płeć i wiek ankietowanych, ale po dane sięgnąć też niemal w głąb ich serc. Jak to możliwe? Wystarczy rozpoznać ich emocje.
Emotional ad positioning and example: New York Times
In 2018, the New York Times conducted a study on the emotions of its readers. This was based on self-learning algorithms and combined with an analysis of feedback collected from readers about how they felt after reading the content of specific articles. The result of this research was an emotion prediction tool that indicates joy, sadness, hope, and 15 other emotions in readers, among others.
Not content to let this tool predict the emotions that NYT readers might potentially experience while reading future articles, the company went straight to selling advertising space. It was offered to owners of products with emotional character close to the emotions contained in the given articles. The possibilities turned out to be impressive: the tool made it possible to examine and create the emotional content of a given article and to better match the marketing message to it.
Marketing content so emotionally targeted and appropriately placed among other content achieved up to 80% better results than classic behavioural targeting (on average by 40%). The tool even made it possible to separate content with negative or disturbing undertones, so as not to add advertising messages that might fit the content or the reader’s profile, but are completely inconsistent with the tone of the text: New York Times.
Emotion targeting – emotional ads: perspectives
The agorithm can be applied not only to the articles contained on this site, but also to news and publications of other types. Therefore, it opened a whole new field for campaign creators. This resulted in 50 campaigns and over 30 million collected feelings, sentiments and emotions. Advertising messages were usually placed next to entertainment or corporate social responsibility content.
Interestingly, similar research was conducted in other editorial offices, including USA Today and The Daily Beast. The analysis was based on phrases (keywords) and emotions related to their meanings, and an attempt to answer the question of what mood current readers of a given text are in based on behavioral analysis of their actions on the website and frequency of returning to specific, emotionally charged content.
USA Today’s research has shown that readers don’t limit themselves to positive news, but read everything. This means you can target your message to them not only when the context is similar to the rest of the content, but also when readers are in a similar mood to the context of the content. Therefore, such a method allows you to more effectively create content for better communication of brands.
The Daily Beast, on the other hand, instead of trying to guess moods, indicates where on the site readers will spend the most time; in these popular places it tries to contextually place the marketing message. All based on positive emotions and negative emotions in advertising.
The future of the advertising market?
The described activities based on data analysis, algorithms and artificial intelligence are beginning to be the future of the advertising and public relations market. How do the market of ordering parties perceive these new solutions? It would seem that with such precise tools for targeting recipients, there is no need to worry about anything else. And yet opinions are divided.
According to some experts, basing a campaign solely on such “bought emotionality” is one-dimensional, restricts and narrows the field of activity and should therefore be associated with other methods of communication. On the other hand, it is an excellent solution for companies looking for safe solutions, making their marketing message more precise and targeting the most determined customers.
Sentimenti and emotional advertising. Identifying emotions in online advertising
Since the New York Times includes emotion ad positioning on its pages, the solution must work and be effective. Positive and negative emotions are taken into account. Is it possible to apply similar mechanisms in Polish?
Until now, this was not at all obvious. Algorithms for automatic processing of our language have been improved to such an extent that they are great for text analysis. But what about the emotions expressed in them? Until now there was no database of words, phrases or even whole texts written in Polish.
That is why the Sentimenti team created it. The database was created in the course of research we talk about on the blog and at academic conferences. It turned out that with good data it is possible to create an effective system of sentiment and emotion analysis and with it – ad positioning.
Interia Emotions – different emotions, one goal
We are now at a similar stage to where the New York Times was about a year ago. We have an application that efficiently analyzes text and the emotions it contains. We have started cooperation with Interia portal – we are creating an emotional map of its thematic services. From here it is only one step closer to taking the overtones of an article into account in ad positioning.
What is very important, emotive ad positioning does not mean additional duties for journalists. We will not tell anyone what emotions to express, because in practice each emotion creates an appropriate environment for ads. Text has a sad meaning? It is best to place an ad with ecological overtones. It expresses fear? This is a good context for pairing the article with an ad for insurance or dietary supplements.
The next step of the Interia Emotions project will be to investigate how exactly emotions in text react with ads. Therefore, when we check this, emotive and effective ad positioning will become a fact. Such a tool will certainly prove useful. Ads positioned based on the content of articles (rather than tracking the activity of Internet users) are less irritating for them.
by Sentimenti Team | May 9, 2019 | Lifestyle
Fashion brands are very popular on social media. When we analyzed the Facebook communication of banks, we didn’t think the topic would be so successful – it’s our most-read post. We hope that hints and tips for improving social media communication can be drawn from it – with an emphasis on “let’s not overdo the display of surprise in official posts.” Now we want to show that we can study emotion on fanpages from different industries, including fashion.
Fashion brands on Facebook
Social media is now the most widely used way to maintain daily communication with customers. Even if they don’t bring direct purchase profits (here a newsletter still works better) they influence the perception of the brand by the wide audience. In short, they set a tone, including an emotional one.
We took a look at the Facebook activity of several Polish brands throughout 2018:
-
- high-profile (Vistula, Monnari),
- casual (Reserved, House, H&M),
- youth (Cropp / LPP),
- patriotic (Red is Bad).
We assume that the tone of their posts will vary, after all, brands want to create their image and react to who they are or what their audience is doing. First, we had to select a few companies with active followers. To do this, we compared the numbers of likes and comments under their posts. The size of the bubble showing the brand’s position reflects the number of posts. In this respect, all the companies we selected are very similar. According to the ratio of likes to comments (like to comment ratio), the best performers are those profiles where this ratio approaches 1.
We decided to analyze the profiles of: Reserved, House, Red is Bad, Cropp, H&M and Monnari. The first four are very similar in terms of Facebook activity, while H&M and Monnari not only stand out from the rest, but are also kind of opposites.
Emotions in fashion brand posts
How different are the various clothing brands? The chart below shows how they compare to the average. For example, a value of 60% for anticipation (orange emotion) in the case of House (black line) means that this company expresses this emotion in its posts that much more often than average. By the same token, -40% joy in the case of Red is Bad (violet) tells us that the brand expresses this emotion significantly less often than others.
Fashion brands create their image on Facebook as environmentally conscious (H&M), very cool (Cropp), elegant and friendly (Monnari), patriotically committed (Red is Bad). The differences between them can also be seen in the results of the sentiment and emotion analysis. Red is Bad expresses a lot of negative emotions: fear, disgust, sadness, anger. Much more than any other company.
House, on the other hand, heavily promotes its future activities while expressing surprise and expectation. Reserved seems to express a very “model” set of emotions, usually staying around the average (0% line) – just what we have come to expect from the communication of an everyday brand, aimed at a very wide audience. Cropp’s profile also has a very similar tone.
Emocje klientów
Facebook is used to communicate directly with the customer, but also with the brand. Observers, private individuals and other companies comment on official posts. What emotions do they express?
Let’s first look at the results of the sentiment analysis. Fashion brands, or rather their customers, seem similar to each other – the differences usually reach 10%, while those between emotions in posts reached 60%. Only Monnari outweighs the others in terms of positive sentiment (20% more than average). House turned out to be a model brand in this comparison, performing at the average level.
Being a model pays off: fashion brands Reserved and Cropp kept their posts within the average intensities of each emotion – and so do those commenting on these statements. Monnari, confirming the results of the sentiment analysis, stands out above the average in terms of joy and anticipation. Perhaps this was influenced by the competition under the slogan “I feel best…”. H&M receives a lot of trepidation in the comments – it’s mostly about complaints and questions about whether it’s possible to buy clothes from the ending collection. The most confidence is expressed by Red is Bad customers.
Fashion brands and their communication with the customer
For now, we know how brands differ. But what about the relationship, fit or rift, between the company and its customers? What is the ratio of emotions in comments to those in posts?
The chart above shows that customers always express more negative sentiment than the brand itself – an expected result. The brand does not complain and complain. But that, among other things, is why it has social media, so that it can quickly receive them from customers and be able to publicly show how efficiently it solves problems. And yet… In the case of Monnari and Red is Bad, this ratio is close to 1, which means that customers complain very little, almost not at all. They are faithful consumers of products and brand statements. What’s fascinating is that these are the only companies where commenters are even slightly more positive than the brand itself.
Fashion brand communication vs customer communication
In the case of Red is Bad, it may be about comments about soccer (the brand talked to observers about the World Cup) and the fact that it itself expresses a lot of negative emotion. However, this trend is observed throughout the year, except for the first quarter, so it is not affected by a single event. In the case of Monnari, we observe satisfied customers writing about when they feel best. We see this trend especially in the third and fourth quarters of 2018.
Finally, our most complicated graph – the relationship between the intensity of emotions in comments and posts. Red color means that a particular emotion appeared in the comments under the company’s posts twice as often. Gray – that it was about the same or a little less.
We immediately see two interesting cases.
H&M has received far more fear than it has expressed – and this has been the case for all quarters of 2018. In addition, commenters also expressed a lot of anger in the first and third quarters of last year – H&M’s customers use the company’s Facebook more often than others to seek help, report problems, and request refunds.
Monnari, on the other hand, shows the opposite, very positive trends. Customers express a lot of joy and (especially in the second and third quarters) expectations in the comments. They are confident that the company and its products are something good, pleasant for them.
We can also observe reverse trends between Reserved and Cropp and Red is Bad when it comes to the emotion of fear. In the case of the first two brands, it is rather expressed by customers. In the case of patriotic clothing – the retailer itself.
Emotions of fashion brands and their customers – conclusions
Monnari and Red is Bad are two brands aimed at completely different target groups. However, they have proven to communicate with their customers most efficiently. They receive positive comments from them, and seem very attuned to their audiences in terms of the tone of their mutual communication.
H&M’s Facebook situation turned out to be the most complicated. This brand received a lot of negative emotion in 2018, although it expressed itself in a moderate way. The other everyday brands and those aimed at a wide audience, Reserved, Cropp and House, stayed around average in both the emotion expressed in posts and that received in comments.
As in the case of banks, it turned out that customers tune into a company’s communications – unless the company lets them down. Then they don’t focus on reading and responding to its communications, but instead express their own opinions, often strongly negative.
Brand monitoring and emotion analysis
This is our next post showing how emotion analysis sheds interesting new light on about various companies in the market. Previously, we examined banks and their Facebook communications. We also examined how various beauty brands are talked about – and which ones are given warmer feelings than others. Sentiment analysis worked well in both the beauty industry, whose representatives differ little from each other, and the heavily diversified entertainment industry.
Sentiment and emotion analysis is a direct insight into the mechanisms that control consumer behavior of customers. That is, our decisions to like something on Facebook, sign up for a newsletter, and finally buy something. If we are not convinced by the emotional overtones of a brand’s communication, if it does not seem sincere to us, we will not want to listen to it. In this study, we found that the customized, out-of-the-ordinary communications of two extremely different companies hit the mark. Their customers wrote a great deal of positive comments on Facebook.
by Agnieszka Czoska | Mar 14, 2019 | Sentimenti research
Each data analysis is aimed at understanding what information it contains. Has something changed, or is there a difference between A and B? Do changes in A correlate with those in C or D? Only these steps allow us to draw conclusions about the results.
First stage: measurement. What is the text?
The above statement also applies to the analysis of emotions or sentiment. Its first stage is the MEASUREMENT, checking how many and what kind of emotions we find in a given text or set of them. The result of a simple emotion measurement shows the intensity of each of Plutchik’s 8 basic emotions supplemented by positive and negative sentiment and arousal (overall emotional temperature of the text). Sometimes we can afford to interpret it already at this stage. We did it in one of our first entries, where we analyzed short ads (what is important, we have already managed to improve the way the results are presented). By analyzing the ads we wanted to show something characteristic for the whole type of texts: the most important emotions are joy and trust, only at the very beginning of the story about the product the creators allow themselves to remember the negative ones – to show the hardships of life before the era of the best shampoo or grease in the world.
The correct results of the Emotional Measurement are those that are consistent with people’s feelings, after all, each of us is an expert on feelings. Our tool owes its correctness to the participants of research on emotions in Polish, which we conducted according to the best scientific standards.
Measurement is only the first step towards understanding the message and the emotions it contains. When we deal with many similar texts or collections of texts, we have to do something else. We want to find out which shop has the best opinions? Which version of our marketing content expresses the most enthusiasm or best shows interest in the subject? Which of the texts in the “Beauty” section will delight, move or warn the reader? We are talking about COMPARISON.
The second stage: comparison. Does this text differ from the average?
Comparison is perhaps the most important stage in the analysis of emotions – thanks to it we not only find out what the text is like, but also how it compares with others. We can compare directly – as we did when writing about lipsticks and lipsticks. Then we were interested in which of the topics has an advantage in terms of positive emotions and whether this difference is statistically significant. However, comparing several or a dozen or so different cosmetic brands cannot be done in this way, it would not be the correct approach. That is why in the text about beauty companies we used a comparison to the average – we needed some kind of background measurement, so-called baseline. This approach will be useful, for example, when comparing shops and brands. We then answer the question which brand has better or worse results than most of the industry.
The most general type of baseline would be the sum of emotions that characterize not only the domain, portal or texts of a given author, but simply language. In linguistics, the so-called Polyanna effect is known, which is that there are more positive than negative expressions in every language. Not only in the dictionary, but also in what we say – this effect expresses quite a general tendency of our minds to spend time and energy rather on pleasant things. In our research we very often see this tendency – joys and trust are emotions that appear in the greatest intensity not only in advertising. The fact that language has its emotional mean all the more reason to draw conclusions only based on comparison and not on the measurement itself.
Third stage: trends. What do emotions do?
The analysis of emotions is also about tracking changes in time, i.e. monitoring emotions. We can check whether sadness or revulsion show a growing trend, i.e. there are more and more of them in statements on a given topic or in the opinions of customers. If we notice a trend, which is statistically significant, we can predict what will happen in the future and if by chance it does not mean an impending crisis (depending on the slope of the trend line).
At this stage it is also possible to go beyond the data from the Sentimenti tools. We started with something simple, accessible and yet untouched by others – we compared the emotional temperatures of mentions of listed companies with the prices of their shares, published publicly. Sentistock is great, it allows you to determine what the investor mood really is and how it translates into stock market fluctuations.
This part of the analysis of emotions depends entirely on who and for what purpose wanted to examine the overtones of the text, the notes, the conversation. We have also managed to show which emotions correlate positively with reactions on Facebook and Twitter – that is, how to write, so that the observers would like to like or comment on the post. However, we might as well ask how emotions correlate with remembering information from the text. Studies on the psychology of emotions, including those conducted by our colleagues from LOBI, indicate that the overtones of the text have an impact on what and how well we remember. Correlation between customer feedback and online store sales? Our tools are designed for this type of research.
Why so many stages?
Emotions were not created for themselves. This is our advisory mechanism: they tell us what action to take. Tversky and Kahneman did not receive the Nobel Prize for their research, but for showing that the consumer, including the stock market, is not rational. This statement tells us two things:
- emotions shape the market,
- we need good tools and methods to study this impact.
Trying to understand the emotions “on the eye” we won’t know more than the average customer wanting to buy a new computer, reading all the available reviews and then deciding on the brand for which he or she has (and had) the warmest feelings. Maintaining scientific standards, checking whether differences and trends are statistically significant and even better correlate with other, harder indicators is the best way to find out. After all, we live in the era of big data and data analysis.
by Agnieszka Czoska | Jan 23, 2019 | Sentimenti research
In this read we want you to meet the idea behind the unique solution that we came up with. It works wider than popular sentiment analysis tools used today for monitoring internet activities and more. Why? Instead of measuring sentiment, we focus on emotions. What does the emotion analysis offer that sentiment analysis does not? Why do we need as many as 8 emotions to describe, or even predict somebody’s state of mind, moods, future actions etc.? And what could you possibly learn whilst knowing them? Let us find out.
What emotions does Sentimenti analyse?
In Sentimenti we have implemented our tools for using Robert Plutchik’s model of emotions. It reveals 8 atavistic, adaptive emotions that help a human being (and any other life form) to survive and create the base for developing far more complex emotional experiences.
The Plutchik model contains two positive emotions: joy and trust, two ambivalent ones: surprise and expectation, and 4 rather, so to speak, negative: sadness, fear, repulsion and anger. Each of them has its meaning, leading the person into an action, praise, criticism, need or surprise. We discuss these emotions one by one.
What is the result? By analysing all the 8 basic emotions, we can precisely assess how much your brand differs in the eye of Internet users, trace down customer opinions on products and services, find out on searched phrases, respond quickly to a communication crisis or compare the company to competitors, amongst the others. But sometimes we also love to have some fun checking on the emotional change during and after popular TV shows display, examining stock market reports reactions, an impact certain political, social or cultural event has and so on.
Sentiment analysis of joy and sadness
Joy and sadness are like black and white, sweet and sour or light and the darkness – a simple division into positive and negative.
Joy reflects a wide range of positive reactions and is related with a smile, the moment when we simply like something. Understood this way, it seems to be similar to a “positive sentiment” (as interpreted by sentiment analysis tools), but the key here is the intensity. Commonly understood joy (“positive sentiment”) is associated with a strong positive reaction to something. Our solution focuses on and lets you find out about any praise components that influence the levels of joy. Including the everyday courtesy.
Sadness is opposite. It describes the loss, a sense of loneliness and the need of comfort, sometimes is even being referred to the person’s ask for help. Together with the joy it forms a contrasting pair in Plutchik’s emotion circle.
The Plutchik model has the psychological background. According to the researches, expressing both emotions at the same time with a similar intensity proves an internal struggle, a very mixed attitude of the text’s author to the subject. It means the person is in unhealthy or somewhat uncomfortable, confusing circumstances. The comparable intensity of positive and negative sentiment cannot be interpreted this way.
The interpretation of joy and sadness levels in this case are different than the levels measured by sentiment analysis tools. In Sentimenti we use two models of text overtones, so we can measure it all. We also count the relationship between different emotions and sentiment. A correlation (we use the r-Pearson measure here) greater than 0.6 is called strong, and close to 0.9 means that the two variables are basically the same. We always measure the relationship between joy and positive sentiment and sadness and negative sentiment for broader cntext and more precise data collection. Depending on the subject, positive or negative sentiment can take almost entirely from a single emotion, but also as the result of many different emotions being expressed by Internet users at once.
The results concerning sadness and joy do not have to be directly related to those obtained in the analysis of sentiment – which also shows that it is the result of many different emotions being expressed in the texts at the same time. We are able to tell you what possibly is behind the joy and sadness.
6 other basic emotions
So now you know the joy and sadness are not just a simple sentiment, but can be developed from other, even complex emotions. We have taken a binary model and put I against the one with 8 categories. The two are already described, where are the other six? We will show what they do and why they differ from simple positive or negative sentiment.
Trust is expressing a sense of security, expecting something to happen the way we want to. It also covers a sense of community, a closer relationship, finding one’s place in the group, a feeling of mutual similarity etc.
Repulsion is an expression of disgust, strong criticism and aversion. When showing it, to us something is outrageous, alien or immoral. It is a strong emotion connected with the reaction of rejection and avoiding something. Many offensive nicknames that describe socially unacceptable groups are associated with repulsion.
Anger – another strong emotion, and very negative one. Instead of avoidance, it is associated with attack and sometimes leads into the aggression. In this way we express threats, but also dissatisfaction. It is accompanied by curses and shouting (in speech, in writing it can be expressed with stronger words).
Fear, as in life, is accompanied by danger, threat and risk. It is associated with escape, a desire to hide. It is also a cry for help.
Surprise comes up when our predictions don’t come true or something unexpected just happens to us. When combined with joy, it gives admiration, and with sadness – disappointment. It can have very different intensity, from a slight surprise to (also associated with fear) panic.
Expectation – the last of the emotions we describe. The opposite of surprise because it means making predictions and believing that they will come true. It can therefore be associated with anxiety or excitement, so it is also ambivalent.
8 emotions make sense
Describing the overtones of a text, portal or brand awareness on the scales of 8 emotions gives you a lot of information. Sometimes only three emotions from the whole model may matter the most, but you will only learn this when having an insight into the whole experience’s spectrum.
Emotions in the titles of portals are very different in terms of the sound of the start page (more in this entry)
First, the sentiment analysis is something different from the emotion analysis, yet we are talking here about two complementing models. Based on the results of one of them, one can predict to some extent the results of the other. Emotional analysis offers a much better insight into what actually checked texts communicate and what kind of consequences they may bring on. For example, an anger is a better catalyst for conflict or popularity loss than sadness. A decrease in trust is more dangerous than a decrease in joy. The graph above shows how different emotions are placed on information portals depending on their character and target group.
Individual emotions are not only differently described by us, but also differ qualitatively in the reader’s perception of the text (we examined it on 22 thousand people) and in the intention of its author. More trust does not necessarily mean more joy – these are very different feelings and can sometimes turn out to be mutually exclusive. These are basic emotions, so they should be independent of each other. At the same time, they form a system and sometimes interact, even if one displaces the other. If you want to know more about emotion analysis, we have also written about go od practices to draw valuable knowledge from measuring emotions with Sentimenti tools.
by Agnieszka Czoska | Oct 9, 2018 | Politics and Social
At SENTIMENTI, we deal with eight emotions – joy, sadness, anger, disgust, trust, expectation, surprise and fear. They can be divided into positive and negative, today we will deal with the latter. We were interested, among other things, because in our previous entry it turned out that the average polarization of emotions towards politicians interested in us was mostly negative.
