What does Twitter Say about Self-Regulated Learning? Mapping Tweets from 2011 to 2021
Last active
January 24, 2022 08:47
-
-
Save slate-dev/8f59772a790e5a3ed70788fab70d5343 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"id": "f1fc655e-15e1-4ae6-8866-79964ceebff3", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# this script for generating the word cloud\n\n", | |
"import numpy as np\n", | |
"import pandas as pd\n", | |
"from wordcloud import WordCloud\n", | |
"import matplotlib.pyplot as plt" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"id": "ee70fafd-3437-487c-9249-608bdfd20f76", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"df = pd.read_feather('tweets_lemmatization.fz').explode('lemma_tokens')\n", | |
"df = df.loc[df['lemma_tokens'].str.len() > 3]\n", | |
"df['created_at'] = pd.to_datetime(df['created_at'])\n", | |
"df" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"id": "f5754367-cc5e-4f3e-81e2-b83f8ee987cf", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"replacement_mapping_dict = {\n", | |
" \"selfregulated\": \"self-regulated learning\",\n", | |
" \"selfregulate\": \"self-regulated learning\",\n", | |
" \"selfregulation\": \"self-regulated learning\",\n", | |
" \"regulation\": \"self-regulated learning\",\n", | |
" \"self\": \"self-regulated learning\",\n", | |
" \"regulate\": \"self-regulated learning\",\n", | |
" \"learning\": \"self-regulated learning\",\n", | |
" \"learn\": \"self-regulated learning\"\n", | |
"}\n", | |
"df[\"lemma_tokens\"].replace(to_replace = replacement_mapping_dict, inplace = True)\n", | |
"df = df.loc[~df['lemma_tokens'].isin(['self-regulated learning', 'student', 'help'])]\n", | |
"df = df.loc[~df['lemma_tokens'].str.contains('\\d', regex=True)]\n", | |
"df['year'] = df['created_at'].dt.year\n", | |
"df = df[['year', 'lemma_tokens']]\n", | |
"\n", | |
"df = (df\n", | |
" .groupby(['year', 'lemma_tokens'])\n", | |
" .size()\n", | |
" .to_frame('size')\n", | |
" .sort_values(by=['year', 'size'], ascending=False)\n", | |
" .reset_index()\n", | |
" .groupby(['year'])\n", | |
" .head(100)\n", | |
" .sort_values(by=['year', 'size'], ascending=True)\n", | |
")\n", | |
"\n", | |
"print(df)\n", | |
"\n", | |
"years = df['year'].drop_duplicates().sort_values()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"id": "378cf99e-76d2-40a4-98fc-7ef96bfb03d6", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"df.to_csv('wordcloud.csv', index=False)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"id": "7c972f04-af2c-4bda-aa7a-5510a70d9d43", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"wordclouds = []\n", | |
"min = df['size'].min()\n", | |
"max = df['size'].max()\n", | |
"d = np.log(10 + max/min)\n", | |
"for year in years:\n", | |
" conf = df.loc[df['year'] == year]\n", | |
" data = {}\n", | |
" prev = 0\n", | |
" for r in conf.iterrows():\n", | |
" key = r[1]['lemma_tokens']\n", | |
" count = r[1]['size']\n", | |
" prev = prev + np.log(10 + count - prev)\n", | |
" data[key] = np.log2(2 + count)\n", | |
" width = 1240\n", | |
" height = 584\n", | |
" if (year == 2021): \n", | |
" width = 2480\n", | |
" height = 584\n", | |
" wordcloud = WordCloud(relative_scaling=0.5, width=width,height=height, max_words=100, background_color=\"white\").generate_from_frequencies(data)\n", | |
" wordclouds.append([year, wordcloud])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"id": "68dedbe8-6d47-43f4-b61c-6dec1b483626", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import math\n", | |
"# Create and generate a word cloud image:\n", | |
"# lower max_font_size, change the maximum number of word and lighten the background:\n", | |
"fig = plt.figure(figsize=(8.3, 11.7), dpi=300, facecolor=\"white\")\n", | |
"plt.axis(\"off\")\n", | |
"\n", | |
"x = 1\n", | |
"y = 0\n", | |
"j = 1 + len(wordclouds) / 2\n", | |
"for w in wordclouds:\n", | |
" c = 2\n", | |
" n = x\n", | |
" if (w[0] == 2021): \n", | |
" c = 1\n", | |
" n = 6\n", | |
" plt.subplot(int(j), c, n).set_title(w[0], y = -0.18, fontsize=12)\n", | |
" plt.plot()\n", | |
" plt.axis(\"off\")\n", | |
" x = x + 1\n", | |
" plt.imshow(w[1], interpolation=\"bilinear\")\n", | |
"# plt.tight_layout(h_pad = 1.5, w_pad = 0)\n", | |
"# plt.tight_layout(rect=(0,0,0.75,1), pad = 0)\n", | |
"plt.subplots_adjust(left=0, bottom=0, right=1, top=1, wspace=0, hspace=0.2)\n", | |
"plt.savefig('wordcloud.png', pad_inches = 0, bbox_inches='tight', facecolor=fig.get_facecolor(), edgecolor='none')" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3 (ipykernel)", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.9.7" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 5 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment