Skip To Content

    8 Things We Learned From 10 Million Inauguration Emoji

    Data finally proves: Trump is (Pouting face emoji)

    During Donald Trump's inauguration ceremony, we asked you to answer a series of questions on BuzzFeed using only emoji. Over the period of a few hours, we received hundreds of thousands of responses, tens of thousands of distinct emoji sequences, and a whopping 10 million emojis. Here's what we learned.

    1. This is us: ๐Ÿ˜ญ ๐Ÿ’ฉ ๐Ÿ˜ก ๐Ÿ‘Ž ๐Ÿ˜ฑ and ๐Ÿ‘.

    These were the most commonly used emojis: ๐Ÿ–• ๐Ÿ˜ญ ๐Ÿ’ฉ ๐Ÿ˜ก ๐Ÿ‡บ ๐Ÿ‘Ž ๐Ÿ‡ธ ๐Ÿ˜ฑ ๐Ÿ‘

    One of the most surprisingly popular emoji was this turtle: ๐Ÿข. It typically appeared with either a banknote (๐Ÿ’ต) or the US flag (๐Ÿ‡บ๐Ÿ‡ธ).

    These were some of the most popular emoji pairs:

    - Man ๐Ÿ‘จ + woman ๐Ÿ‘ฉ

    - Loudly crying face ๐Ÿ˜ญ + pouting face ๐Ÿ˜ก

    - Heavy black heart โค + woman ๐Ÿ‘ฉ

    2. The official Donald J. Trump emoji is ๐Ÿ˜ก.

    Brendan Smialowski / AFP / Getty Images + BuzzFeed

    The data spells it out loud and clear: The pouting face emoji has been chosen by you all as the official Donald J. Trump emoji.

    Responses varied significantly. On the one hand, some of our readers were clearly not thrilled with the election outcome ๐Ÿ˜ณ๐Ÿ˜ก๐Ÿ˜ค๐Ÿ˜ซ๐Ÿ˜ซ๐Ÿ˜ซ๐Ÿ˜ซ๐Ÿ˜ซ, but on the other, many were ๐Ÿ˜€๐Ÿ˜๐Ÿ˜˜๐Ÿ˜™๐Ÿ˜ก๐Ÿ˜ก๐Ÿ˜ก๐Ÿ˜ก. Both sides of the spectrum used the same emoji to represent Trump ๐Ÿ˜ก๐Ÿ˜ก๐Ÿ˜ก.

    3. ๐Ÿ‡บ๐Ÿ‡ธ bridges the divide!

    Gilad Lotan, BuzzFeed

    One way for us to gauge the diversity of sentiment among all responses is to model the emoji sequences as a network graph. Graphs give us a great way to understand relationships between items and identify clusters โ€” regions of dense connectivity.

    The following graph represents the relationships between all emojis submitted in response to the question "What do you think about Trump's speech?" Each circle (node) represents an emoji, the lines between them (edges) represent the number of times two emojis appeared together in a sequence, and the colors represent cluster: clear groups of emojis that appeared many more times with each other, compared to the rest. (high resolution image)

    Gilad Lotan, BuzzFeed

    We can see that the green region includes reactions that are clearly supportive of the speech (smiling face, thumbs up, grinning, etc.), while the blue, orange, and purple reactions represent clearly negative sentiment.

    What's especially interesting here is the central position that the US flag ๐Ÿ‡บ๐Ÿ‡ธ holds, effectively acting as a bridge between the two sides of the network. It is the emoji that's most used with those supporting โ€” ๐Ÿ‘๐Ÿป๐Ÿ˜‚๐Ÿ™Œ๐Ÿป๐Ÿ˜€๐Ÿ˜ƒ๐Ÿ‘๐Ÿป๐Ÿ‘Œ๐Ÿป๐Ÿ‡บ๐Ÿ‡ธ โ€” and opposing โ€” ๐Ÿ˜๐Ÿ™„โ˜น๐Ÿ˜ฐ๐Ÿ˜ญ๐Ÿ‡บ๐Ÿ‡ธ โ€” Trump's speech. (high resolution image)

    The full network graph is pretty amazing.

    Gilad Lotan, BuzzFeed

    This is effectively a mapping of the relationships between all of the emojis across all responses to our questions. Again, we see clear clusters of emojis:

    * In purple: negative emotions, which are, unsurprisingly, clustered together. If you respond with a crying face, you're likely to also use the angry face, or the Canadian flag.

    * In blue: positive responses. If you use something like a smiling face or a thumbs-up emoji, you're likely to use the victory hand or the flexed biceps emoji.

    * In orange: faces and people. If you use a face in your response, you're likely to use other faces.

    The full graph data is available for download here (nodes, edges). Let us know what you find!

    4. Skin tone emojis are ๐Ÿ”ฅ.

    Gilad Lotan, BuzzFeed

    If we look at the distribution of skin tone usage across those emojis that do allow for varying skin tones, we see fairly heavy usage across all categories.

    Many responses included a diverse set of skin tones. ๐Ÿ‘ฉ๐Ÿฟ๐Ÿ‘ฉ๐Ÿพ๐Ÿ‘ฉ๐Ÿฝ๐Ÿ‘ฉ๐Ÿผ๐Ÿ‘ฉ๐ŸปโœŠ and โœŠโœŠ๐ŸปโœŠ๐ŸผโœŠ๐ŸฝโœŠ๐ŸพโœŠ๐Ÿฟ๐Ÿ‡บ๐Ÿ‡ธ were responses to our question "What do you think is the greatest thing about America today?

    5. You're pretty clever with your emoji sequences.

    These emoji sequences consistently came up in your answers to the question "What are the greatest things about America today?"










    These emoji sequences consistently came up in your answers to the question "What are the most important issues in the US today?"







    And...can you help me decipher this one?

    ๐Ÿ…ฟ๐Ÿ…พ๐Ÿ…พ๐Ÿ…ฟ๐Ÿ‘๐Ÿ‘…๐Ÿ‘ ?

    6. No one knows what the Russian flag looks like.

    Gilad Lotan, BuzzFeed

    Using a measure called pointwise mutual information (PMI), we can start to gauge the relationship between items that appear in sequences. PMI is a measure of association used in information theory and statistics. It is a great way to find collocations and associations between words in sentences โ€” and also emojis in sequences.

    A high PMI score between two items means that the probability of co-occurrence is slightly lower than the probabilities of occurrence of each of the items separately. For example, word pairs such as "puerto" + "rico," "pay" + "attention," and "nobel" + "prize" have high PMI values. These are combinations of words that are closely affiliated with each other.

    By computing the PMI scores for both the thumbs-up and thumbs-down characters in relation to all other emojis, we can effectively organize the range of relationships (similarities and differences) between each sentiment (pro/con) and the rest of the emojis.

    The Russian flag, ๐Ÿ‡ท๐Ÿ‡บ , interestingly enough, sees low PMI values with both ๐Ÿ™‚ and ๐Ÿ˜ž , likely due to the fact that it doesn't consistently appear with one of them. With that, you can see how this plot helps us organize the range of emotions and emojis, from the happy, smiling, and joyous to the saddened, disappointed, and confused faces. (high resolution image)

    7. So many ways to say "Canada, here we come."






    8. ๐Ÿ…พ๐Ÿ…ฑ๐Ÿ…ฐใ€ฝ๐Ÿ…ฐ๐Ÿ”™๐Ÿ”œ

    I'll leave you with that, and also these two open positions on our Data Science team!

    * Data Scientist (NY or LA)

    * Data Science Intern (NY or LA)