AI + MarketingAssociationsCase StudyConsumer PerceptionInternational Market ResearchMarket Research

UNICEF’s Social Media Optimization: The Refugees Cluster (Part 2 of 3)

By 17. February 2020 March 4th, 2020 No Comments
Natural disaster association

After conducting a baseline analysis of UNICEF’s posts for social media optimization (SMO). This led to the extrapolation of three clusters from UNICEF’s 2,917 posts. 

In this post, we will focus on the second of those clusters, the Refugees + Migrants cluster. 

Top 3 clusters identified by our embedding models based on top words

Top 3 clusters identified by our embedding models based on top words

To see how associations and optimization approaches vary across clusters, take a look at what we found in the Family analysis and the School + Education analysis

Ultimately, our goal is to identify exactly which associations drive successful social media posts and images within the Refugees + Migrants cluster. Why? Because, by knowing what works and what doesn’t, SMO can reach its maximum. 

Big Data, Machine Learning, and Social Media Optimization

In this article, we will take a look at the following, in order to establish strong and weak points of UNICEF’s existing approach to social media:

  • Text analysis of this cluster
    • Text associations that led to HIGH engagement
    • Text associations that led to LOW engagement 
  • Examples of text+associations that were SUCCESSFUL
  • Examples of text+associations that were UNSUCCESSFUL
  • Image analysis for this cluster
    • Image associations that generated HIGH engagement
    • Image associations that generated LOW engagement
  • Examples of Images
    • SUCCESSFUL images
    • UNSUCCESSFUL images

After going through all of these analysis, we will be able to say, with absolute confidence, what leads to low or high engagement in UNICEF’s social media posts. 

Text Analysis for Refugees and Migrants Cluster

In this section, we will take a look at what kind of text was correlated with high and low engagement. A key component of social media optimization is knowing what works and what doesn’t. 

By analyzing the text, we will get a better understanding of which themes working within this cluster and which do not. 

To do this, the 223 posts which fell within the Refugees and Migrants cluster were analyzed. 

For the Refugees and Migrants cluster, correlations of associations appearing in text of successful posts (represented in yellow bars) and unsuccessful posts (gray bars).

For the Refugees and Migrants cluster, correlations of associations appearing in text of successful posts (represented in yellow bars) and unsuccessful posts (gray bars).

Text Associations with High Engagement 

Our analysis showed that there were definitely some predominant themes that were associated with post success and engagement. 

The posts that were most successful were identified to have the following associations:

  • Discrimination: Equality, oppression, marginalize, minority, racial, racism, solidarity, injustice, advocate
  • Political: Government, opposition, politician, declare, constitutional, oppose, elect, advocate, congress
  • Treaty: Agreement, negotiation, pact, ratify, signatory, ceasefire, ratification, declaration, multilateral

The following associations were also positively ranked:

  • Expertise: specialist, professional, expertise, skilled, provide, technician, service, expert, competent
  • Dedication: empower, commitment, motivate, aspiration, passionate, passion, dedication, enthusiasm, nurture

With this information, in the future, it is possible to draft posts that invoke these associations. For future posts, UNICEF should draft text that specifically correlates with these high-engagement associations. 

Text Associations with Low Engagement 

Just as there are associations that are associated with high engagement, there are associations that are linked to low engagement. 

The posts that were below average in their success were associated with:

  • Natural disaster: torrential_rain, tsunami, typhoon, hurricane, flood, earthquake, torrential, rainstorm, cyclone
  • Scream: yell, groan, shriek, gasp, sob, loudly, mutter, giggle, cry
  • Water body: river, lagoon, shoreline, shore, sea, cove, coastal, beach, village
  • Illness: illness, symptom, disease, acute, sufferer, pneumonia, debilitate, ailment, syndrome
  • Temperature: heat, cold, warm, cool, spin-dry, soak, melt, water, wet

From these associations, Temperature had the most negative effect on success.  

Thus, future Facebook posts should be written in such a way as to avoid these associations as they are linked to low engagement and success rates. 

Examples of Successful Posts and Associations

Below, you can see how the highly successful associations (like Discrimination, Political, and Treaty) are identified and measured in real-life Facebook posts categorized within the Refugees+Migrants cluster:

The green highlights are used to visualize the strength of the goal association and the word. This is made possible via the in-browser NEURO FLASH chrome extension.  The extension works while you are logged in to your account. For your free 3-day trial, sign-up here.

Now, let’s take a look at a few examples of what successful posts within the Refugees and Migrants cluster look like:

Discrimination Association

Higher engagement was correlated with associations of Discrimination. Below are samples of posts that rate high in the Discrimination association: 

Discrimination association

Discrimination association

Discrimination association

Discrimination association

Discrimination association

Discrimination association

Political Association

Higher engagement was correlated with associations of Political. Below are samples of  post that rate high in the Political association:

Political association

Political association

Political association

Political association

Political association

Political association

Treaty Association

Higher engagement was correlated with associations of Treaty. Below are samples of posts that rate high in the Treaty association:

Treaty association

Treaty association

Treaty association

Treaty association

Treaty association

Treaty association

Examples of Unsuccessful Posts and Associations

Below is the analyzed text of a few posts which showed to have low engagement scores, representing the following associations: temperature, illness, and water body

Water body association

Water body association

Temperature association

Temperature association

Illness association

Illness association

Image Analysis for Refugees and Migrants Cluster

To supplement the text analysis, an image analysis was also performed, using 223 posts.

 For the Refugees and Migrants cluster, correlations of image associations appearing in successful posts (represented in yellow bars) and unsuccessful posts (gray bars)

For the Refugees and Migrants cluster, correlations of image associations appearing in successful posts (represented in yellow bars) and unsuccessful posts (gray bars)

Image Associations with High Engagement 

The images that were most successful in the Refugees and Migrants cluster were associated with the following:

  • Natural disaster: torrential_rain, tsunami, typhoon, hurricane, flood, earthquake, torrential, rainstorm, cyclone
  • Temperature: cold, warm, cool, spin-dry, soak, melt, water, temperature, wet
  • Nutritious: nutritious, meat, veggies, eat, food, poultry, meal, foodstuff, veggie
  • Adventure: embark, journey, adventure, treacherous, adventurer, adventurous, explore, unexplore, expedition
  • Playground: inflatable, swim, playground, swing, pool, outdoor, bounce, swim_pool, rope

Image Associations with Low Engagement

The images that were least successful in the Refugees and Migrants cluster were associated with the following:

  • Discrimintation: oppression, discrimination, marginalize, minority, racial, racism, solidarity, injustice, advocate
  • Hostility: instigate, ensue, intensify, confrontation, quell, amid, hostility, incite, erupt
  • Ignorance: truth, ignorance, fact, ignorant, misguide, believe, merely, misunderstand, deceive

In the next section, we will take a look at what these associations look like as images. 

Examples of Images 

Now, let’s move away from abstract ideas and take a look at what these associations look like as images. In this section, we will see what successful and unsuccessful images look like. 

Successful Images and Associations

Unsuccessful Image Posts and Associations

Below are images, and their respective associations, that showed to have the lowest levels of engagement:

Conclusion

With big data insights and machine learning tools, you can pinpoint exactly to what contributed to the high success of certain UNICEF’s posts. By isolating the associations and stylistic factors that are found in successful posts and repeating them, UNICEF’s SMO  strategy will automatically improve.

Now, we know exactly what factors contribute to the success of a UNICEF social media post within the Refugees + Migrants. Thus, for this cluster, specific guidelines can be established, defining which associations for texts and images are most effective.

In future posts, texts and images can be crafted in order to invoke the associations which we know are correlated with success and engagement. 

Therefore, piece by piece, a detailed SMO strategy is forming which outlines which factors to use and avoid. 

Related Blog Posts: Social media optimization case studies

For more info, check out these related blog posts: 

 

Top 3 clusters identified by our embedding models based on top words

Top 3 clusters identified by our embedding models based on top words

 

 

Jonathan T. Mall

Author Jonathan T. Mall

Jonathan is a cognitive Neuropsychologist turned entrepreneur, obsessed with understanding what and why people think. He founded NEURO FLASH to help communicators find the best words, phrases, and images to connect with their target audience most effectively.

More posts by Jonathan T. Mall

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.