{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "https://www.clarin.si/repository/xmlui/handle/11356/1048\n", "https://github.com/words/emoji-emotion" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import pandas as pd\n", "import math\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | Emoji | \n", "Unicode codepoint | \n", "Occurrences | \n", "Position | \n", "Negative | \n", "Neutral | \n", "Positive | \n", "Unicode name | \n", "Unicode block | \n", "
---|---|---|---|---|---|---|---|---|---|
0 | \n", "😂 | \n", "0x1f602 | \n", "14622 | \n", "0.805101 | \n", "3614 | \n", "4163 | \n", "6845 | \n", "FACE WITH TEARS OF JOY | \n", "Emoticons | \n", "
1 | \n", "❤ | \n", "0x2764 | \n", "8050 | \n", "0.746943 | \n", "355 | \n", "1334 | \n", "6361 | \n", "HEAVY BLACK HEART | \n", "Dingbats | \n", "
2 | \n", "♥ | \n", "0x2665 | \n", "7144 | \n", "0.753806 | \n", "252 | \n", "1942 | \n", "4950 | \n", "BLACK HEART SUIT | \n", "Miscellaneous Symbols | \n", "
3 | \n", "😍 | \n", "0x1f60d | \n", "6359 | \n", "0.765292 | \n", "329 | \n", "1390 | \n", "4640 | \n", "SMILING FACE WITH HEART-SHAPED EYES | \n", "Emoticons | \n", "
4 | \n", "😭 | \n", "0x1f62d | \n", "5526 | \n", "0.803352 | \n", "2412 | \n", "1218 | \n", "1896 | \n", "LOUDLY CRYING FACE | \n", "Emoticons | \n", "
5 | \n", "😘 | \n", "0x1f618 | \n", "3648 | \n", "0.854480 | \n", "193 | \n", "702 | \n", "2753 | \n", "FACE THROWING A KISS | \n", "Emoticons | \n", "
6 | \n", "😊 | \n", "0x1f60a | \n", "3186 | \n", "0.813302 | \n", "189 | \n", "754 | \n", "2243 | \n", "SMILING FACE WITH SMILING EYES | \n", "Emoticons | \n", "
7 | \n", "👌 | \n", "0x1f44c | \n", "2925 | \n", "0.805223 | \n", "274 | \n", "728 | \n", "1923 | \n", "OK HAND SIGN | \n", "Miscellaneous Symbols and Pictographs | \n", "
8 | \n", "💕 | \n", "0x1f495 | \n", "2400 | \n", "0.765726 | \n", "99 | \n", "683 | \n", "1618 | \n", "TWO HEARTS | \n", "Miscellaneous Symbols and Pictographs | \n", "
9 | \n", "👏 | \n", "0x1f44f | \n", "2336 | \n", "0.787130 | \n", "243 | \n", "634 | \n", "1459 | \n", "CLAPPING HANDS SIGN | \n", "Miscellaneous Symbols and Pictographs | \n", "
10 | \n", "😁 | \n", "0x1f601 | \n", "2189 | \n", "0.796151 | \n", "278 | \n", "648 | \n", "1263 | \n", "GRINNING FACE WITH SMILING EYES | \n", "Emoticons | \n", "
11 | \n", "☺ | \n", "0x263a | \n", "2062 | \n", "0.798634 | \n", "128 | \n", "449 | \n", "1485 | \n", "WHITE SMILING FACE | \n", "Miscellaneous Symbols | \n", "
12 | \n", "♡ | \n", "0x2661 | \n", "1975 | \n", "0.763695 | \n", "102 | \n", "448 | \n", "1425 | \n", "WHITE HEART SUIT | \n", "Miscellaneous Symbols | \n", "
13 | \n", "👍 | \n", "0x1f44d | \n", "1854 | \n", "0.812126 | \n", "213 | \n", "460 | \n", "1181 | \n", "THUMBS UP SIGN | \n", "Miscellaneous Symbols and Pictographs | \n", "
14 | \n", "😩 | \n", "0x1f629 | \n", "1808 | \n", "0.826214 | \n", "1069 | \n", "336 | \n", "403 | \n", "WEARY FACE | \n", "Emoticons | \n", "
15 | \n", "🙏 | \n", "0x1f64f | \n", "1539 | \n", "0.793848 | \n", "124 | \n", "648 | \n", "767 | \n", "PERSON WITH FOLDED HANDS | \n", "Emoticons | \n", "
16 | \n", "✌ | \n", "0x270c | \n", "1534 | \n", "0.790480 | \n", "173 | \n", "476 | \n", "885 | \n", "VICTORY HAND | \n", "Dingbats | \n", "
17 | \n", "😏 | \n", "0x1f60f | \n", "1522 | \n", "0.764977 | \n", "170 | \n", "676 | \n", "676 | \n", "SMIRKING FACE | \n", "Emoticons | \n", "
18 | \n", "😉 | \n", "0x1f609 | \n", "1521 | \n", "0.844833 | \n", "151 | \n", "513 | \n", "857 | \n", "WINKING FACE | \n", "Emoticons | \n", "
19 | \n", "🙌 | \n", "0x1f64c | \n", "1506 | \n", "0.790600 | \n", "152 | \n", "358 | \n", "996 | \n", "PERSON RAISING BOTH HANDS IN CELEBRATION | \n", "Emoticons | \n", "
20 | \n", "🙈 | \n", "0x1f648 | \n", "1456 | \n", "0.738881 | \n", "238 | \n", "350 | \n", "868 | \n", "SEE-NO-EVIL MONKEY | \n", "Emoticons | \n", "
21 | \n", "💪 | \n", "0x1f4aa | \n", "1409 | \n", "0.806704 | \n", "101 | \n", "424 | \n", "884 | \n", "FLEXED BICEPS | \n", "Miscellaneous Symbols and Pictographs | \n", "
22 | \n", "😄 | \n", "0x1f604 | \n", "1398 | \n", "0.794973 | \n", "191 | \n", "426 | \n", "781 | \n", "SMILING FACE WITH OPEN MOUTH AND SMILING EYES | \n", "Emoticons | \n", "
23 | \n", "😒 | \n", "0x1f612 | \n", "1385 | \n", "0.857621 | \n", "819 | \n", "266 | \n", "300 | \n", "UNAMUSED FACE | \n", "Emoticons | \n", "
24 | \n", "💃 | \n", "0x1f483 | \n", "1344 | \n", "0.852765 | \n", "59 | \n", "237 | \n", "1048 | \n", "DANCER | \n", "Miscellaneous Symbols and Pictographs | \n", "
25 | \n", "💖 | \n", "0x1f496 | \n", "1263 | \n", "0.762239 | \n", "54 | \n", "254 | \n", "955 | \n", "SPARKLING HEART | \n", "Miscellaneous Symbols and Pictographs | \n", "
26 | \n", "😃 | \n", "0x1f603 | \n", "1206 | \n", "0.734782 | \n", "86 | \n", "361 | \n", "759 | \n", "SMILING FACE WITH OPEN MOUTH | \n", "Emoticons | \n", "
27 | \n", "😔 | \n", "0x1f614 | \n", "1205 | \n", "0.866146 | \n", "559 | \n", "263 | \n", "383 | \n", "PENSIVE FACE | \n", "Emoticons | \n", "
28 | \n", "😱 | \n", "0x1f631 | \n", "1130 | \n", "0.773313 | \n", "298 | \n", "319 | \n", "513 | \n", "FACE SCREAMING IN FEAR | \n", "Emoticons | \n", "
29 | \n", "🎉 | \n", "0x1f389 | \n", "1125 | \n", "0.743636 | \n", "43 | \n", "207 | \n", "875 | \n", "PARTY POPPER | \n", "Miscellaneous Symbols and Pictographs | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
939 | \n", "🕥 | \n", "0x1f565 | \n", "1 | \n", "0.811966 | \n", "1 | \n", "0 | \n", "0 | \n", "CLOCK FACE TEN-THIRTY | \n", "Miscellaneous Symbols and Pictographs | \n", "
940 | \n", "♙ | \n", "0x2659 | \n", "1 | \n", "0.342857 | \n", "0 | \n", "1 | \n", "0 | \n", "WHITE CHESS PAWN | \n", "Miscellaneous Symbols | \n", "
941 | \n", "▿ | \n", "0x25bf | \n", "1 | \n", "0.432836 | \n", "0 | \n", "1 | \n", "0 | \n", "WHITE DOWN-POINTING SMALL TRIANGLE | \n", "Geometric Shapes | \n", "
942 | \n", "⚃ | \n", "0x2683 | \n", "1 | \n", "0.918919 | \n", "0 | \n", "1 | \n", "0 | \n", "DIE FACE-4 | \n", "Miscellaneous Symbols | \n", "
943 | \n", "✽ | \n", "0x273d | \n", "1 | \n", "0.992701 | \n", "0 | \n", "0 | \n", "1 | \n", "HEAVY TEARDROP-SPOKED ASTERISK | \n", "Dingbats | \n", "
944 | \n", "📼 | \n", "0x1f4fc | \n", "1 | \n", "1.000000 | \n", "0 | \n", "0 | \n", "1 | \n", "VIDEOCASSETTE | \n", "Miscellaneous Symbols and Pictographs | \n", "
945 | \n", "🕐 | \n", "0x1f550 | \n", "1 | \n", "1.000000 | \n", "1 | \n", "0 | \n", "0 | \n", "CLOCK FACE ONE OCLOCK | \n", "Miscellaneous Symbols and Pictographs | \n", "
946 | \n", "🀄 | \n", "0x1f004 | \n", "1 | \n", "1.000000 | \n", "0 | \n", "0 | \n", "1 | \n", "MAHJONG TILE RED DRAGON | \n", "Mahjong Tiles | \n", "
947 | \n", "✾ | \n", "0x273e | \n", "1 | \n", "0.023256 | \n", "0 | \n", "1 | \n", "0 | \n", "SIX PETALLED BLACK AND WHITE FLORETTE | \n", "Dingbats | \n", "
948 | \n", "✬ | \n", "0x272c | \n", "1 | \n", "0.955224 | \n", "0 | \n", "0 | \n", "1 | \n", "BLACK CENTRE WHITE STAR | \n", "Dingbats | \n", "
949 | \n", "🆑 | \n", "0x1f191 | \n", "1 | \n", "0.983607 | \n", "0 | \n", "1 | \n", "0 | \n", "SQUARED CL | \n", "Enclosed Alphanumeric Supplement | \n", "
950 | \n", "✫ | \n", "0x272b | \n", "1 | \n", "0.923729 | \n", "0 | \n", "0 | \n", "1 | \n", "OPEN CENTRE BLACK STAR | \n", "Dingbats | \n", "
951 | \n", "🕔 | \n", "0x1f554 | \n", "1 | \n", "0.742424 | \n", "1 | \n", "0 | \n", "0 | \n", "CLOCK FACE FIVE OCLOCK | \n", "Miscellaneous Symbols and Pictographs | \n", "
952 | \n", "❣ | \n", "0x2763 | \n", "1 | \n", "0.471429 | \n", "0 | \n", "0 | \n", "1 | \n", "HEAVY HEART EXCLAMATION MARK ORNAMENT | \n", "Dingbats | \n", "
953 | \n", "➱ | \n", "0x27b1 | \n", "1 | \n", "0.704348 | \n", "0 | \n", "1 | \n", "0 | \n", "NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ... | \n", "Dingbats | \n", "
954 | \n", "🆕 | \n", "0x1f195 | \n", "1 | \n", "0.669118 | \n", "0 | \n", "1 | \n", "0 | \n", "SQUARED NEW | \n", "Enclosed Alphanumeric Supplement | \n", "
955 | \n", "➢ | \n", "0x27a2 | \n", "1 | \n", "0.242647 | \n", "0 | \n", "1 | \n", "0 | \n", "THREE-D TOP-LIGHTED RIGHTWARDS ARROWHEAD | \n", "Dingbats | \n", "
956 | \n", "↕ | \n", "0x2195 | \n", "1 | \n", "0.735632 | \n", "0 | \n", "1 | \n", "0 | \n", "UP DOWN ARROW | \n", "Arrows | \n", "
957 | \n", "📫 | \n", "0x1f4eb | \n", "1 | \n", "0.384615 | \n", "0 | \n", "0 | \n", "1 | \n", "CLOSED MAILBOX WITH RAISED FLAG | \n", "Miscellaneous Symbols and Pictographs | \n", "
958 | \n", "🉐 | \n", "0x1f250 | \n", "1 | \n", "0.031250 | \n", "0 | \n", "0 | \n", "1 | \n", "CIRCLED IDEOGRAPH ADVANTAGE | \n", "Enclosed Ideographic Supplement | \n", "
959 | \n", "♊ | \n", "0x264a | \n", "1 | \n", "0.327586 | \n", "0 | \n", "1 | \n", "0 | \n", "GEMINI | \n", "Miscellaneous Symbols | \n", "
960 | \n", "🈂 | \n", "0x1f202 | \n", "1 | \n", "0.466667 | \n", "1 | \n", "0 | \n", "0 | \n", "SQUARED KATAKANA SA | \n", "Enclosed Ideographic Supplement | \n", "
961 | \n", "🎰 | \n", "0x1f3b0 | \n", "1 | \n", "0.421687 | \n", "1 | \n", "0 | \n", "0 | \n", "SLOT MACHINE | \n", "Miscellaneous Symbols and Pictographs | \n", "
962 | \n", "҂ | \n", "0x482 | \n", "1 | \n", "0.519231 | \n", "1 | \n", "0 | \n", "0 | \n", "CYRILLIC THOUSANDS SIGN | \n", "Cyrillic | \n", "
963 | \n", "╤ | \n", "0x2564 | \n", "1 | \n", "0.634615 | \n", "1 | \n", "0 | \n", "0 | \n", "BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE | \n", "Box Drawing | \n", "
964 | \n", "➛ | \n", "0x279b | \n", "1 | \n", "0.011628 | \n", "0 | \n", "1 | \n", "0 | \n", "DRAFTING POINT RIGHTWARDS ARROW | \n", "Dingbats | \n", "
965 | \n", "♝ | \n", "0x265d | \n", "1 | \n", "0.280000 | \n", "0 | \n", "1 | \n", "0 | \n", "BLACK CHESS BISHOP | \n", "Miscellaneous Symbols | \n", "
966 | \n", "❋ | \n", "0x274b | \n", "1 | \n", "0.888889 | \n", "0 | \n", "1 | \n", "0 | \n", "HEAVY EIGHT TEARDROP-SPOKED PROPELLER ASTERISK | \n", "Dingbats | \n", "
967 | \n", "✆ | \n", "0x2706 | \n", "1 | \n", "0.557252 | \n", "0 | \n", "1 | \n", "0 | \n", "TELEPHONE LOCATION SIGN | \n", "Dingbats | \n", "
968 | \n", "📔 | \n", "0x1f4d4 | \n", "1 | \n", "0.814815 | \n", "0 | \n", "0 | \n", "1 | \n", "NOTEBOOK WITH DECORATIVE COVER | \n", "Miscellaneous Symbols and Pictographs | \n", "
969 rows × 9 columns
\n", "