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
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).
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
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
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
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
Temperature 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)
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
Temperature association
Natural disaster association
Nutritious association
Unsuccessful Image Posts and Associations
Below are images, and their respective associations, that showed to have the lowest levels of engagement:
Discrimination association
Hostility association
Ignorance association
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:
- Baseline analysis: The first blog post of the UNICEF series which explains the baseline analysis and basic procedures followed.
- Family: See our detailed analysis on the Family cluster for the factors that led to success.
- School + Education: Check out the analysis on the School + Education cluster for a specific report on what worked best for this theme.
Top 3 clusters identified by our embedding models based on top words
