It’s that time of year again: Oscar season. So much to get excited about! Fifteen years later, I’m still verklempt remembering Björk’s iconic swan dress! And I’m not alone in my anticipation: In just the past month there have been over 2.7 million mentions of the Academy Awards. Social media is buzzing with conversation on who deserves recognition.

Which brings me to my main question: If your brand wants to stand out in the entertainment industry, don’t you think you’re missing out on the big picture if you’re not utilizing social? Consumers share their likes, dislikes, needs, and desires in passionate language on any subject that you can dream up on social media. So, how can you harness the power of social media to understand your brand’s reception in the wild?

This two-part series will help you understand how to use social media listening to identify, listen, and engage with your audience and keep them happy. In this post, I’ll show you how to take a concept (The Academy Awards) and craft a story – but that’s not all.

Social is not just a resource to measure campaign success or brand reception: it can also be a powerful predictor of the next best thing. And since you and I are presumably not members of the Academy of Motion Picture Arts and Science, why not turn to social to see what people are saying about the Oscars? Can we use social listening to predict who should win?

Most Mentioned Terms About The Academy Awards

A quick glance at a word cloud reveals a lot on the overall picture, as well as where we can further focus our analysis to better understand what fans want, need, and expect.


One of the things that makes NetBase a great social media listening tool is the clarity of quick visualizations for understanding your information environment. What’s interesting? What’s surprising? And how can brands utilize this information to minimize negative publicity?

(Spoiler alert: This is the subject of part two in this series – which will take a look at the surprising insight of #OscarsSoWhite, and how can brands can address and mitigate adverse sentiment effectively.)

Back to part one!

From there, I clicked on StoryScope to add sentiment to the mix. It’s an efficient way to reconstruct a word cloud and re-visualize it with sentiment and volume. And while we have a clear picture that the majority of fans are abundantly pleased, there is a sizable unhappy crowd too.



The most common mentions with positive sentiment terms focus on Oscar nominations and categories and not on specific actors.

Congratulations 113,471
#Oscars 108,813
#OscarNoms 105,003
@TheAcademy 98,228
oscar isaac 12,702
Leading Actor nominees 11,855
Original Song nominees 11,008
Best Picture nominees 8,891
#GoldenGlobes 7,621
Leading Actress nominees 7,197
Adapted Screenplay nominees 5,927
Animated Feature nominees 5,927
Directing nominees 5,504
Mafia won 5,504
won an Oscar 5,080
Original Screenplay nominees 4,657
Foreign Language Film 4,234
Language Film nominees 4,234

What about people? Who is the most discussed according to social?


Here’s where the refinement bit really comes in handy. Our next dive shows me that Oscar Isaac, Oscar Wilde, and Oscar de la Renta, amongst other outliers, are pretty big. But none of them have an Oscar nomination. (And Oscar Wilde has been six feet under for over a century!) We can add them as term exclusions to get a more accurate depiction of the topic and sentiment:

Leo 4,850
Lady Gaga 3,490
Leonardo DiCaprio 3,040
Jamie Foxx 1,740
Jennifer Lawrence 1,480
Oscar Isaac 1,270
Chris Rock 860
Ellen 790
Sam Smith 680

Leo and Lady Gaga are the highest in positive mentions. One initial surprise was Jamie Foxx: the actor, while not nominated, is being discussed as the “Oscar winner” who rescued a driver from a burning vehicle! (Go Jamie!) As I mentioned in my analysis of the State of the Union speech, strong analytics is an iterative process and requires refinement – but NetBase makes this a seamless experience, with quality results for your efforts. We can remove Jamie Foxx and move on, but it’s significant to see how his accomplishments and clout are mentioned during Oscar season.

How to Understand Your Audience?

The analysis methodology I suggest is not restricted to The Oscars but can help you understand any audience or topic component of interest. A glance at sentiment drivers can add texture to our analyses and help social media teams plan and execute engagement strategies that are tailored to your audience’s needs.

Most mentioned behaviors on The Oscars:



Most mentioned emotions on The Oscars:


You don’t have to be a marketer to understand that these two word clouds present two contrasting visualizations of our audience. On one hand, we see that Oscar mentions are positively and overwhelmingly focused on congratulations and accolades, which makes sense. The emotions, however, present the “Aha!” moment: jarring red text with negative sentiment, including “boycott,” “not attend,” and “not watch.”

The possibilities of what you can do with these insights are endless – especially when you seek answers to questions like: “What else is this audience passionate about?”

And how do you handle a crisis like the one brewing above before it snowballs into something embarrassing or distracting? Sentiment drivers are one key ingredient to understanding your audience so you can create an engagement strategy to outstep or maneuver around potentially damaging PR.

I’ll talk about others, and dive deep into negative sentiment and sensitive issues around crisis management, in my next post as we get closer to The Oscars.

Ready to run your own analysis about your brand? We can get you started today!

Image from Alan Light

Premier social media analytics platform

Expand your social platform with LexisNexis news media

Power of social analytics for your entire team

Media analytics and market intelligence platform

Enrich your media analytics with social data

Media coverage for historical & real-time monitoring

Data streams & custom KPIs for advanced data science

AI, Image Analytics, Reporting Tools & more

Out-of-the-box integration with other data sources