Share this
How to use social media intelligence to boost your brand sentiment analysis
by Hephzibah Dutt on December 9, 2022
With 2023 just around the corner, it's easy to get wrapped up in the projected top marketing trends for 2023. However, before getting lost in devising influencer and experiential marketing strategies and upping your digital content game, make sure you have a strong grip on a foundational brand management metric – brand sentiment.
In this article, we go over some of the basics of brand sentiment analysis. We then share examples of how you can use social listening tools to acquire fast and organic perspectives on your brand sentiment, and use those same tools to go deeper – to understand the reasons behind consumer sentiment towards your brand.
What is brand sentiment?
In marketing, sentiment refers to the attitudes or feelings behind consumer engagements with your brand. In this sense, sentiment is highly simplified and generally categorized as positive, negative or neutral sentiment.
Brand sentiment is the net attitude towards a brand: it accounts for the sum of all positive sentiment minus all negative sentiment towards any given brand. In fact, brand sentiment is often referred to as net brand attitude.
Brand health is closely related to brand sentiment. It is a measure of how well a company or brand lives up to what it promises its consumers. A company that faithfully delivers on the products and services it promises its customers will generally have excellent brand health.
Why is brand sentiment analysis important?
Since brand sentiment is a measure of how consumers feel about your product, business, or service, brand sentiment is prophetic – it forecasts and impacts upcoming impacts to sales, loyalty, and customer retention.
- Brand sentiment analysis works in real-time: sentiment changes quickly and, as a result, impacts businesses quickly. Having brand sentiment data at your fingertips can help you respond and thus, keep your consumers engaged.
- Brand sentiment analysis helps you understand your audience: While social monitoring helps you keep track of what people are saying about your brand, more robust brand sentiment analysis can provide deeper insights into why your consumers like or dislike what they do. You can use these insights generated by social listening to shape your product and marketing to better resonate with your target audience.
- Brand sentiment analysis improves customer satisfaction: Once you understand the “what and why” motivating brand sentiment, you can proactively take measures to address factors that might be frustrating your customers.
- Brand sentiment analysis will shape your PR strategies: The more you know about how consumers feel about your brand, the better you’ll be able to craft relevant, authentic and immediate messaging. You’ll even discover topics and interests and concerns that your target audience needs you to address.
How to measure brand sentiment
Whether delivered online or offline (by means of surveys, forums, panels), brand sentiment can be measured by three main indicators: willingness to recommend, ratings, and direct feedback.
In the not-too-distant past, companies would have dedicated teams in place to gather and analyze feedback and sentiment. However, with over 62% of the world’s population online, and 81% of those users owning at least one social media profile, brands can have faster and more streamlined access to brand sentiment data.
In fact, while both online and offline behaviors can contribute to brand sentiment, online behaviors capture the most organic and fastest route to acquiring measurable brand sentiment.
Susan D. Coco, Director of Consumer and Commercial Insight at Colangelo suggests that focus groups are relatively limited in their capacity to provide true consumer insights. You can learn more about why Colangelo – specialists in brand attachment and marketing – use our social listening platform, Infegy Atlas, for social media analytics instead.
The bulk of online activity that contributes to brand sentiment analysis occurs in the form of online conversations: consumers posting on their social profiles, customers leaving reviews on product and service websites, and even employees discussing their experiences working with companies.
With such an abundance of organic consumer and brand feedback available on the internet, measuring and analyzing brand sentiment requires reliable and fast social listening and social media analysis software.
How to use social listening tools for brand sentiment analysis
Social listening software can analyze the variety of textual elements that demonstrate sentiment: tone, emojis, punctuation, context and more. Truly robust platforms with excellent textual analytical capabilities can take you beyond the black-and-white nature of positive/negative sentiment to identify specific emotions. We explain this in more detail below.
It’s important to remember that social media monitoring tools are different from social listening tools. Social media monitoring platforms specialize in tracking the performance of owned channels, whereas social listening tools provide social media intelligence on a much broader scale. They are especially tuned to the search for consumer insights and metrics on brand sentiment.
Below, we’re going to demonstrate how to use social listening for brand sentiment analysis and more, using our consumer insights tool, Infegy Atlas.
At its simplest, a brand sentiment score or rating is presented as the percentage of positivity or negativity displayed in the online conversations around a brand.
Let’s begin with a simple example of net positive brand sentiment for a long-time favorite American CPG brand, Oreos. Using Infegy Atlas, you can conduct a general search and analysis on the entire conversation around the brand, Oreo (Figure 1).
Figure 1: Sentiment trend graph on the conversation around Oreos; Infegy Atlas data.
Sentiment trend examples
The trend graph above shows dips and rises in the positive sentiment with which consumers discuss the Oreo brand, but its average sentiment remains high at 70%. This isn’t unexpected: during these months, the company maintained its brand health, nothing occurred to change consumer interest in the chocolate biscuit and sweet cream treat, and there were no PR crises to sway positive sentiment towards the company.
A more complicated brand sentiment example would be the sentiment trends around Beyond Meat. Beyond Meat launched into the plant-based CPG foods scene in 2009. In the past, it generated high positive sentiment with its promise to maintain sustainability while delivering a plant-based burger that would be indistinguishable from real meat.
Social listening reveals some recent fluctuations in sentiment (the company laid off 4% of their workers in August), but there was a drastic downturn in September 2022, when it became embroiled in a PR crisis. Beyond Meat’s Chief Operations Officer was arrested for an assault during which he bit a person’s nose – an irony consumers posting online couldn’t ignore.
Social listening analysis reveals the exact degree and immediacy of the impact this had on sentiment. The trend graph below shows how the positive sentiment trend crashed immediately (Figure 2).
Figure 2: Sentiment trend graph for Beyond Meat; Infegy Atlas data.
Here, social listening data provides immediate access to not only the changes in sentiment, but also depicts the timeline in which sentiment drops: from a 90% positive on Sept. 4, 2022 to 28% positive 2 weeks later.
Sentiment analysis of select social posts
Within a robust social listening analytical tool, you don’t need to make assumptions about what’s generating the negative sentiment. You can zoom into a selection of posts from the relevant period and read for yourself why consumers are responding negatively in conversations connected to your brand (Figure 3 ).
Figure 3: Select posts from the period reflected in Figure 2; Infegy Atlas data.
Top positive and negative keywords
Since sentiment is rarely just back or white, social listening tools can also show you individual topics that are associated with conversations that are analyzed as more positive or more negative. In the case of Beyond Meat, positive topics in the conversation are things that Beyond Meat and its partners want to share (plant-based, vegan, growth), and the negative topics involve the executive’s arrest (Figure 4).
Figure 4: Top postive and negative keywords in the conversation around Beyond Meat; Infegy Atlas data.
How to use social listening to go beyond just sentiment
Some social listening tools can take you well deeper, beyond just positive, neutral and negative sentiment. They can analyze posts and articles to give you metrics on the actual emotions contained in the online conversation..
For example, Infegy Atlas can analyze whether the positivity or negativity stems from specific feelings such as love or disgust. State-of-the-art linguistic analysis technology can detect these emotions in text, aggregating their appearance across the conversation, and then displays the appearance of each emotion as a percentage. Infegy Atlas can discern ten emotions: trust, joy, love, disgust, anger, anticipation, sadness, surprise, fear, and hate.
We examined the conversation around the brand Subaru – specifically, Subaru Outback – to look at the emotions within the conversation. According to consumer data from Wards Intelligence, Subaru has some of the highest customer loyalty ratings in the business. Marketing data also confirms that Subaru’s marketing campaigns have been very successful and rank amongst highest performing commercials that are associated with likeability, watchability, and relevance.
Social listening supports the consumer data. It also gives an organic and unprompted picture of the emotions with which Subaru Outback owners discuss their vehicle. The investment Subaru puts into its products is validated by how Trust shows up in 27% of the all posts around Subaru Outbacks (Figure 5). Joy is the second highest emotion in the conversation, appearing in 16% of all posts.
Figure 5: Social conversation around "Subaru Outbacks" depicts that users discuss the vehicle with a high percentage of Trust; Infegy Atlas data.
How to use social listening to measure engagement as an indicator of sentiment
Ron Shevlin, an analyst at Aite Group, offers this definition of customer engagement: “Repeated interactions that strengthen the emotional, psychological, or physical investment a customer has in a brand.”
In the same way that brand sentiment and brand health are related, customer sentiment and customer engagement are directly related to each other. Diving into social listening data on customer engagements point directly to factors that influence brand sentiment.
On social media, consumers engage with a brand by liking, commenting and sharing brand messaging. Social listening measures this engagement by aggregating the likes, comments and shares and presenting this as this as a single score.
At first glance, this may not seem like a brand sentiment indicator, but it is! Higher customer engagement over time, points to a stronger relationship strength. This is especially valuable when engagements indicate willingness to recommend. In many situations, when social users positively share posts from brands, that’s essentially what they are doing – indicating a willingness to recommend and promote the brand. Users also share posts and ads that they disagree with with negative comments – another reason why having a social media analysis tool with robust linguistic analysis capabilities is so important!
McDonalds announced the McRib sandwich in 1981. Since then, the sandwich has joined and left the McDonalds menu several times. In early October 2022, McDonalds signaled a return of the sandwich with an intriguing tweet, “guess who’s coming back [sic].” That same day, they also tweeted that they would be bringing the McRig, their mobile restaurant, to service thousands of hot meals for people affected by Hurricane Ian (Figure 6).
Figure 6: Engagements graph showing that McDonalds's tweets about the McRib and McRig generated over 9,000,000 likes, comments, and shares; Infegy Atlas data.
In a single day, these two tweets garnered 9,301,953 engagements; this was the highest engagement in three months in the conversation around McDonalds. While a large portion of the posts indicated skepticism that this would indeed be the farewell tour of the McRib, overall sentiment during peak engagement was 55% positive.
Brand sentiment analysis should remain foundational to your marketing strategy
Even as marketing trends ebb and flow, brand sentiment remains a sure foundation on which to shape all your messaging, communication, marketing and PR strategies.
With the ocean of data available through social media, you can use social intelligence gathering and analysis tools to tap into and measure your brand sentiment easily. Most importantly, truly robust social listening tools will take you beyond positive and negative brand sentiment, into the heart of the reasons, feelings, interests and consumer passions driving brand sentiment.
Are you working on a project that requires brand sentiment data? We’d love to hear more and learn how we can help. Schedule a custom demo today!
Additional Contributor: Henry Chapman, Research and Insights Analyst
Share this
- October 2024 (2)
- September 2024 (3)
- August 2024 (4)
- July 2024 (2)
- June 2024 (1)
- May 2024 (2)
- April 2024 (2)
- March 2024 (3)
- February 2024 (3)
- January 2024 (2)
- December 2023 (3)
- November 2023 (4)
- October 2023 (3)
- September 2023 (3)
- August 2023 (4)
- July 2023 (4)
- June 2023 (2)
- May 2023 (4)
- April 2023 (4)
- March 2023 (4)
- February 2023 (4)
- January 2023 (1)
- December 2022 (3)
- November 2022 (4)
- October 2022 (3)
- September 2022 (3)
- August 2022 (2)
- July 2022 (1)
- June 2022 (1)
- April 2022 (1)
- March 2022 (1)
- January 2022 (1)
- December 2021 (1)
- November 2021 (1)
- October 2021 (1)
- June 2021 (1)
- May 2021 (1)
- April 2021 (1)
- March 2021 (1)
- February 2021 (1)
- January 2021 (2)
- November 2020 (1)
- October 2020 (2)
- September 2020 (1)
- August 2020 (2)
- July 2020 (2)
- June 2020 (2)
- April 2020 (1)
- March 2020 (2)
- February 2020 (2)
- January 2020 (2)
- December 2019 (2)
- November 2019 (1)
- October 2019 (1)
- September 2019 (2)
- August 2019 (2)
- July 2019 (1)
- June 2019 (1)
- May 2019 (2)
- March 2019 (2)
- February 2019 (2)
- January 2019 (1)