Actionable Insights to Elevate Your Communications:

Benchmark analysis from PublicRelay.

PublicRelay hosted a live webinar with our SVP of Analytics, Ted Ziemer, and Director of Analytics, Azhar Unwala, to discuss key insights that emerged in the communications landscape of 2022. As your trusted advisor, we want to share actionable insights to help you guide your brand strategy.

Most media analysis relies on automation, but we’ve found that including a human element can provide insights that truly impact your business. We created this exclusive, virtual opportunity to share the results of our communications landscape report that highlights what a human-augmented technology approach can achieve.

By registering for our event, you will learn best practices of top-performing companies so you can elevate your communications strategy and benchmark your brand’s performance against the best in the industry.

• How using your CEO as a spokesperson can make an impact on corporate reputation
• How to tailor your communications strategy to take advantage of the topics your audience cares about while protecting your brand against harmful media coverage
• How best to engage with major stories that shaped the communications landscape of 2022, like inflation, the overturning of Roe v. Wade, and the Russia-Ukraine war

Can technology provide more accurate analysis than humans?

A PublicRelay Partnership with MIT finds that the answer is no.

A study that set human media analysis head-to-head with MIT’s natural language technology processors found that automated solution only had:

• 9% accuracy on detecting key message presence
• 20% accuracy on allocating the correct sentiment
• 33% accuracy on highlighting the precise experience of the customer 

Background

Social media analysis is one of the fastest-growing areas of text analytics.

For efficiency and economical reasons, most media analytics providers in the space rely on automated technology to extract emotion and sentiment.  But can technology actually provide more accurate text analysis than a human?

In collaboration with Toyota Motor NA Energy & Environmental Research Group, PublicRelay and the intelligent minds at the Massachusetts Institute of Technology (MIT) Analytics Lab set out to find an answer.

The Project

Over the course of three months, the MIT Analytics Lab team tested various technologies to:

• Understand which topics car enthusiasts are discussing in relation to alternate-fuel vehicles on Twitter
• Identify “significant” tweets based on topic inference from above.

The goal was to identify tweets that demand further tracking or direct engagement, and formulate messaging that Toyota might use to drive social media conversations themselves.

The Technology

• MIT built two different modeling approaches to interpret the data– Latent Dirichlet Allocation (LDA) and a Biterm Topic Model (BTM).
• For both processes, the MIT team indicated to the machines which words were topically important.
• The processes would then clean up the tweet text by isolating only the most “important” words and analyze those for key messages, sentiment, and experience according to pre-set definitions.

The Results

• The accuracy of the technological solution versus the human in three key measured attributes was only 9% (key message), 20% (sentiment), and 33% (experience).
• While the technology may be useful in eliminating irrelevant posts before humans analyze them, the MIT team found that 80% of their machine-learning work was simply data clean-up — the computer algorithms had a hard time deciphering commonly used symbols in on Twitter, like @, #, and even text emojis.
• Lastly, the study showed how technology did not handle rapidly changing topics well:
  • Analysis over a short time frame fails to detect the quickly‐dissipating influence of one‐off news events and crises.
  • Rapidly emerging issues or breaking news such as the Tesla autopilot crash were slow to be reflected in a model.

Social media analytics that make sense of the conversations happening across social platforms is an essential tool of modern PR. Tracking discussions about specific products, campaigns, and companies using social media analytics tools can provide PR teams with valuable insights into their company’s and competitors’ reputations. However, broader social topics, like ESG, have become increasingly important to stakeholders and are a significant factor in business success.

Read: The Role of Social Media in Public Relations

Communications teams must keep a finger on the pulse of the broad social issues, like sustainability, that impact their industries and align with their target audience’s values. With 500 million tweets sent per day, social media has presented an opportunity for companies by providing an open-source of audience perspectives and attitudes on every topic imaginable, with updates every second.

On the flip side, digesting the sheer amount of social data available while extracting reliable insights is easier said than done. That’s where sampling comes in.

What is sampling in social media analytics?

Sampling in social media analytics is the process of collecting a subset of social media coverage of a specific topic for analysis to infer what the general population is saying about it. Rather than collecting and analyzing every mention, sampling reduces the amount of data to a manageable volume while maintaining the integrity and accuracy of the findings.

For example, let’s say your team wants to know what aspects of ESG people care about most to refine an upcoming campaign. Social media sampling will gather selections of social coverage mentioning ESG topics using a sampling method that accounts for variation across the larger population. That sample of social content will then be analyzed and yield insights that can be applied to the total population.

Why is sampling in social media analytics important?

Sampling in social media analytics is important because it enables communications teams to distill massive amounts of data on a broad topic spanning social media into actionable insights relevant to your industry.

As broader social topics, including ESG and CSR, become more significant facets of companies’ reputations, understanding public discourse and sentiment surrounding these themes is equally as important as tracking your company mentions to managing your brand.

While standard automated social media monitoring tools can track your and your competitors’ social presences, they aren’t designed to accurately analyze mentions of concepts or complex topics. Human analysis, on the other hand, can more accurately capture this kind of content but struggles with the volume of data across social platforms. However, sampling is a statistically validated method for extracting insights from enormous data sets, like the one made available by social media.

How does social media sampling work?

Essentially, sampling is the process of taking and analyzing small (representative) samples of a dataset to draw conclusions about the total population without having to analyze each data point.

Social media sampling uses a statistical method often used in accounting that arranges large quantities of data into groups based on similarities, then draws subsets of data from each group reflective of the general population. The subset of data is then cleaned and analyzed to generate insights that can be extrapolated to larger populations.

How can you apply insights from social media sampling to your communications strategy?

Social values and priorities can change from one viral Tweet to the next. Understanding the topics and subtopics receiving the most positive coverage and engagement across social media in near-real time can guide your campaigns and help you to capitalize on opportunities to promote your key messages at exactly the right moment.

Here are a few considerations for making the most of social media sampling:

Determine the topics that are relevant to your industry

Consider your range of stakeholders and their priorities. Generally, sampling for social media analysis is best applied to broad topics related to corporate reputation (e.g., CSR, workplace environment, etc.) or timely social issues (e.g., ESG, DEI, gender equity, data protection, sustainability, etc.).

Each of your stakeholder groups will have differing and, at times, competing interests. Outlining the issues relevant to your industry stakeholders (e.g., consumers may care about sustainability and data protection, while employees value compensation and DEI, and local communities are concerned with CSR) will help you define the topics you’ll benefit from tracking.

Measure subtopics

Analyzing the right subtopics will provide your team with a more nuanced understanding of the conversations surrounding each tracked topic and enable you to finely-tune your messaging.

For instance, when measuring social media discussions around workplace environment, breaking coverage down according to subtopics can tell you whether people currently care most about DEI, compensation, or gender pay equity.

Develop a responsive strategy

Communications guided by insights from sampling social media require a PR team prepared to react quickly to changing social values and adjust messaging accordingly.

The insights made available by sampling social media can highlight what people care about most, when they are talking about it, and how to best frame your campaigns surrounding each topic and subtopic to resonate with your audience.

By having a strategy primed to adapt to abruptly changing views on significant topics, your team can take advantage of the nuanced understanding of social media discourse enabled by sampling.

Inform Your Communications Using Sampling in Social Media Analytics

Effective communications require a nuanced understanding of more than your company’s reputation. Tracking the social topics that span social media platforms can change how you deliver your key messages by capitalizing on the trends and nuances of the conversations surrounding them.

Though social media analytics tools that rely exclusively on technology can’t extract reliable insights on broad social topics, employing a statistically proven sampling method supported by human analysis can.

Not to mention, analyzing text for concepts, sentiment, and linguistic devices (like irony, sarcasm, and slang), often used in social media conversations, requires a human understanding that technology alone can’t match.

At PublicRelay, we apply our human-augmented AI method of media measurement to sampling social media content. By combining advanced technology with human intelligence, our team analyzes each social media topic according to the subtopics, sentiment, and concepts relevant to your industry and company. Click here to amplify your social media analysis using sampling now!

In today’s competitive marketplace, brand awareness matters more for companies than ever before. Social media platforms not only provide a means to boost your brand, but they also generate data that, when used correctly, can steer your PR campaigns towards success.

Read: The Role of Social Media in Public Relations

What is Brand Awareness?

Brand awareness is the level of consumer familiarity with a particular brand’s products, services, or image. Familiarity is what motivates consumers to choose Coca-Cola over other soft drinks. It is the economic moat that wards off competition and ensures customers remain loyal. This is the first stage of the marketing funnel and the key to promoting new products, establishing loyalties, and reviving old brands.

When developing branding campaigns, companies must consider their values, reputation, and the levels of engagement their key messages receive on social platforms. Beyond engagement, brand boosts are about establishing positive relations between a company and its target audience.

Why is Brand Awareness Important?

Brand awareness is important because consumers rely on research and social proof to inform their purchasing decisions. In his TED talk, “The Post-Crisis Consumer,” John Gerzerma labels this phenomenon the “rise of the mindful consumer.” With an abundance of information at their fingertips, consumers can now sift through online reviews and compare influencer testimonials on social media before every purchase. In fact, 67% of the consumer journey now occurs digitally.

For this reason, companies need to use social media channels to build brand awareness positively influence their target audience’s consumer journey in their favor.

Social Media Metrics to Measure Brand Awareness

PR professionals’ branding strategies are most effective when informed by reliable data. Social media provides companies with access to a wealth of information on consumer engagement with and awareness of new campaigns, and influencer pick-up of key messages. With approximately 501 million tweets sent per day, companies are confronted with both a goldmine and a headache when it comes to analyzing the available data. MGP head of digital Eamonn Carey explains, “you can almost get data overload: the challenge is picking out the metrics that matter[…] The smarter brands are taking a step back from the tsunami of data.” 

Amid such large quantities of data, PublicRelay has witnessed an explosion of AI-based tools that help track the key metrics used to measure brand awareness. These metrics can be broken down into four standardized categories:

Exposure and Potential Reach

Exposure and potential reach, which tell the possible number of unique viewers a post may have, are the first data points to consider when attempting to improve your brand recognition across social media platforms.

However, exposure and potential reach should be utilized as baseline metrics as they do not provide enough insight on their own to help steer a PR strategy. For instance, a post could have high impressions, but also receive low or negative engagement. Using exposure and potential reach in conjunction with other metrics, such as engagement, will help you glean more insight from the data at hand.

Engagement

Put simply, engagement is the number of users who interact with a campaign and the degree of that interaction over time. Extrapolating engagement can be done in multiple ways. Often, data analytics tools will create a metric that is a combination of likes, retweets, comments, and shares.

High levels of positive engagement often indicate a healthy relationship with your target audience and a successful branding campaign. However, these metrics also need to be understood within their context. For instance, a post may receive a high number of likes and shares but relatively few comments, indicating that the topic doesn’t stimulate discussion. On the other hand, the motivations for sharing or retweeting your company’s coverage may be negative. For this reason, engagement metrics are just one part of a wide range of data points that need to be taken into consideration.

Impact

Measuring impact on social media refers to the overall changes in consumer behavior and sentiment towards your brand as the result of your PR campaigns. Often companies will compare their initial rates of engagement and exposure to those during and after a campaign. In this case, social media analytics can provide a useful benchmark to inform your next steps.

Further, social media platforms are data treasure troves when it comes to evaluating your brand awareness relative to your rivals. A key goal for any awareness strategy should be about establishing your brand as the central player among competitors.  

Advocacy

In every campaign, influencers are vital to swaying opinions and increasing awareness. Strategists must understand industry influencers’ topical interests and the degree of engagement they can generate.

The appropriate metrics can reveal the extent to which influencers promoted your key messages and help your team to identify the major influencers in the industry. Ultimately, boosting your brand recognition is about intelligent engagement. Find the right influencers and you can reach the audiences that truly matter.

Ensuring Accurate Assessment and Intelligent Engagement

PR teams that engage with this standardized model lay a strong analytical foundation upon which to develop their brand awareness strategies. As Neil Kleiner, former head of social media at Golin argues, “exposure, engagement, impact, [and] advocacy are important, and there are demographic elements to it as well: it’s about reaching 10,000 of the right people, not ten million.” 

Indeed, PR strategists should be looking for intelligent engagement when improving their brands and that means going beyond base-level metrics that are supplied by AI. Although AI is useful for processing large amounts of data, it encounters issues with accuracy and meaning when it comes to nuance and developing insights that matter, and especially when gauging sentiment. 

How is Sentiment Analysis Used for Brand Management?

Sentiment analysis is crucial to brand management when staging a brand awareness campaign. Applying sentiment to the four-baseline metrics is the final element in a PR strategist’s information armory. Receiving high volumes of mentions, retweets, and influencer traction are all signs of growth. However, without an awareness of the sentiment of social engagement, your campaign assessment may be deceptive. 

Sentiment refers to the tone or emotion attached to social media posts or engagement. With the rise of Artificial Intelligence, many products are appearing on the market that offer sentiment analysis with unlimited data pools.

While the tone of your coverage is important, sentiment also extends to social media coverage of your company values and reputational drivers. However, AI cannot accurately identify reputational drivers and value systems that human analysts can. By understanding the kinds of reputational drivers and values that have emerged during a campaign combined with tone, PR strategists can understand how their brand awareness strategies are having a real-time impact. Applying sentiment to the four-baseline metrics through a synthesis of human intelligence and AI tools allows PR teams to pinpoint the positives and negatives of their campaigns to increase brand awareness. 

Using Social Media Analytics the Right Way

When measuring boosts in brand awareness using social media analytics, employing a variety of baseline metrics paired with accurate sentiment analysis will yield the most reliable results.

At PublicRelay, we utilize the four-baseline metrics for a holistic approach that compliments AI systems with purposeful, human-generated insights. Our human-AI hybrid approach focuses on intelligent engagement, whereby we filter out the noise and pinpoint the most valuable insights to help you increase your brand awareness. Click here to learn more.

Sentiment analysis is a term that most PR practitioners and communications professionals have heard of, and perhaps even a tool they use as a part of their strategy. However, many industry pros struggle to fully understand the concept and what it can do for them when implemented effectively.

The applications of sentiment analysis are wide-ranging and impactful. For instance, Brandwatch asserts that “shifts in sentiment on social media have been shown to correlate with shifts in the stock market.” British political magazine New Statesman even used the process to determine that President Joe Biden’s recent 2021 inaugural address was “the angriest ever,” based on key linguistic choices.

What is Sentiment Analysis? 

Sentiment analysis is the process of identifying the tone or emotion attached to a communication. It can also be referred to as “opinion mining” or Emotion AI. Examples of the types of communication that can be analyzed for tone are nonverbal, like facial expressions and body language, and linguistic.

Analyzing the sentiment of linguistic forms of communication starts with examining a sample of text, which is then assigned a value based on the perceived attitude or tone of the communicator. Usually, the values are coded as positive, neutral, or negative so the data can be easily sorted and later visualized and studied for trends.

Why is Sentiment Analysis Important?

Sentiment analysis is important because it can provide you with a better understanding of your earned media coverage and help you reach your messaging goals. The analysis is part of an integral feedback loop that allows communicators to gauge the success of their communications tactics and identify opportunities for improvement.

Measuring the volume of media coverage by topic can only tell you so much. Without knowing the tone of that coverage, teams can’t determine whether their campaign is a success or a failure. For example, if your company experiences a spike in mentions related to product quality, how can you appropriately respond without first knowing whether that coverage is positive or a potential PR crisis, all of which comes down to sentiment?

Lexalytics explains that sentiment analysis can help companies to gauge “public opinion, conduct nuanced market research, monitor brand and product reputation, and understand customer experiences.” Once you have identified your strengths, weaknesses, and opportunities, you and your team can take advantage of all the practice has to offer.

Using AI for Sentiment Analysis

When analyzing text, computers deploy natural language processing and machine learning techniques to attach sentiment to words, phrases, topics, and themes. When an analysis program runs on an article it breaks the text down into these units. The program then identifies components that have been assigned sentiment in the program’s sentiment library (which stores the system’s human-coded values) – or the library entries they are closest to – and assigns a score to each unit. Finally, the system combines the individual scores to generate a multi-layered analysis score that represents the whole article.

As smooth as this process sounds, there are many areas where problems can arise along the way.

The Accuracy of AI Sentiment Analysis

Because AI uses natural language processing and machine learning to automate the process, it’s a useful tool for freeing up your team’s valuable time. However, fully automating your sentiment analysis can compromise its accuracy.

According to the Institute for Public Relations, no method of sentiment analysis will ever be 100% accurate. However, they argue that relying solely on a tech tool to measure sentiment “can be like flipping a coin, or only 50% accurate, since these platforms often struggle to measure more nuanced posts or are unable to filter and interpret the information through the lens of a company or brand.” Similarly, 5WPR estimates that sentiment algorithms are only about 60 percent accurate.

Linguistic Challenges for AI

Toptal has identified four major pitfalls of AI sentiment analysis: irony and sarcasm, negations, word ambiguity, and multipolarity. Some of these pitfalls can be addressed with approaches like machine learning algorithms or deep learning, but no solution is guaranteed to be fully effective.

Sarcasm is an especially deep pitfall, and its prevalence in consumer-generated content, like social media posts, makes it even more important in many sentiment analysis projects. Even humans struggle to comprehend sarcasm sometimes, so it’s no surprise that computers are often tricked by false-positive statements like, “I love the way [company’s] customer service team put me on hold for two hours.” Research shows that numerical sarcasm like in this statement is especially challenging for AI to comprehend due to its effect on a statement’s polarity.

As a media analyst, I often see articles that dive into complex subjects in detail. The more detailed the article, however, the higher the chances that an AI program will be tripped up by common traps like negatory statements, ambiguity surrounding entities, or articles that discuss both the pros and cons of one idea.

These issues demonstrate some of the imperfections of using AI, which can drastically change the narrative of your media analysis and your subsequent tactical decisions.

Adding a human element to your approach can be the solution to avoiding these major data hazards.

Using Humans to Detect Sentiment 

Although using an AI program can help save time, its imperfections can lead to inaccurate results that can impact your communications strategy. Because of these shortcomings, it is essential to include a human perspective to analyze the more linguistically complex elements of your media coverage.

While computers need to be trained to detect subtle context clues, humans have been ‘programmed’ to find them throughout their entire socialized lives, which makes identifying common language tools like irony and negations quite simple. Using human analysts to identify these common contexts and AI to automate the basic tasks that save time can be beneficial for PR professionals as they work to improve the accuracy of their sentiment analysis insights.

The Value of a Hybrid Approach

Both AI and human analyst approaches to sentiment analysis have benefits: AI programs save time with automation, and humans decipher context and increase accuracy. Ultimately, utilizing a combined approach can offer the best of both worlds.

At PublicRelay, our human-AI hybrid approach to media monitoring makes conceptual insights possible. To learn more about using PublicRelay for accurate sentiment analysis, contact us here.

Every communicator knows when a big story is published, every minute matters. Yet many earned media articles leave little impact – while a few pieces drive the entire conversation. But what if you could know in advance which stories will catch fire?

With PublicRelay’s Predictive Alerts, you can. This feature gives your team an email alert that a particular story is likely to take off over social media – hours before it actually does. You and your team gain valuable time with which to craft the perfect response or engage key advocates to amplify the coverage.

The Details

Predictive Alerts uses industry-leading AI to predict whether an article will go viral on social media. If an article is likely to be widely shared, we deliver an email alert straight to your inbox. This gives you time to craft the appropriate media strategy.

The alert operates within a set of search terms defined by you and your analyst, depending on the topic of interest. The scope is completely up to you – search terms are not limited to tracked themes and brand drivers. Your team can keep an eye on important company announcements, key influencers, or monitor major articles on industry topics more broadly.

Strategic Value

Social sharing is a crucial gauge on which topics, outlets, authors, and stories garner the most attention. Knowing about these news hits in advance, your team can:

• Enhance positive news by engaging company advocates and employees to share the story.
• Get ahead of negative coverage with a clear, compelling media response.
• Calm worried executives by demonstrating a disagreeable piece is unlikely to receive much attention.
• Keep track of what’s generating real buzz for competitors or peer companies.

Earned Media in the Social Age

Social media has become a cornerstone of the brand landscape. In a surprising twist, however, this shift to social has only increased the importance of viral earned media. Only half of consumers say they trust paid advertisements – but 92% trust earned media. This trust, coupled with the fact that a majority of social sharing is generated by only a few earned articles, makes identifying viral earned media paramount to staying ahead in brand awareness. Predictive Alerts are the best way to glimpse into your media future – what will you do with the extra time?

With the rise of artificial intelligence and ensuing hype, many companies in the media intelligence industry and beyond began touting their use of AI. But the story often stops there without further explanation.

Communicators don’t have to be data scientists, but it is worth asking your media intelligence provider how they employ AI. In the world of textual media analytics, there are best practices as in any other industry. If your provider is not following them, it could have serious consequences for the accuracy of your communications data.

Media Analytics Best Practices

Use Ongoing Supervised Machine Learning

Cultural conversation changes quickly. The meaning and connotation of words are situational and evolve over time. This is why several studies have found artificial intelligence employed in the media analytics space must be supervised. One study from communications experts at the University of Wisconsin-Madison and the University of Georgia found, “the combination of computational processing power with human intelligence ensures high levels of reliability and validity for the analysis of latent content.” Another from researchers at the University of California at Berkeley and Northwestern University found that unsupervised machine learning, “does not perform well in picking up themes that may be buried within discussions of different topics” and therefore missed several mentions of the topic they were tracking of economic inequality. The concept of inequality, whether in the economy or in the workplace, might very well be something a communicator would want to track – and certainly other nebulous concepts like it.

Computers can improve at processing language, but they need to be told what’s right and wrong. A computer cannot tell when the use of sarcasm in an article contradicts the normal sentiment of a word it has already learned to label positive, so it will continue incorrectly analyzing your content until it is corrected.

That’s why media intelligence providers cannot take a “set it and forget it” approach to AI. A constant feedback loop is required to educate the computer in the nuances of language. If the data set remains static, it will make your analysis inaccurate and irrelevant.

Target Analysis Specifically to Your Company and Your Perspective

The most accurate communications analysis comes from ongoing supervised machine learning targeted specifically to your business. Every organization has different goals, challenges, and perspectives on the world. Two companies can read the same news article or social post and analyze it completely differently based on their point of view. A solar energy company and electric utility company would categorize and tone the same article about energy regulation very differently. If you use the same data set across clients, you run into the same problem again in that the computer will continue analyzing content as it originally learned, not accounting for the context of what a specific organization cares about.

At PublicRelay, we perform client specific media analysis leveraging ongoing supervised machine learning to ensure that our clients are getting the most accurate data possible. This accurate, contextual analysis tailored to their business goals enables them to not only understand what they’ve done, but yields insights that tell them what to do next.