You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
ZSI_Reconnect_China/TODO.ipynb

135 lines
3.9 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"source": [
"# TODO"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "markdown",
"source": [
"# So far:\n",
"## WOS\n",
"- WOS: sample dataset (see query for details) -> only Peoples' Republic of China /to be specified!/ ~11-13.000 initial record\n",
"- WOS - METRIX merge --> filter for articles indexed by METRIX\n",
"- Affiliations and Country (from adresses) extraction\n",
"- Filter for articles with 'foreign collaboration' at least two authors from different regions (EU, CH)\n",
"- Fuzzy association between Institute and Country (Affiliation - Address (institution) - Adress (Country)\n",
"## PATSTAT\n",
"- PATSTAT scope extraction (initial: 2011-2024, has both EU and China /to be specified!/ in appln-person person map --> 'foreign collab'\n",
"- I love harmonized entities, harmonized even further (sector)\n",
"- Fetched CPC description data taxonomy, merged with PATSTAT: lost around one percent of the records"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "markdown",
"source": [
"# WOS current query:\n",
"\n",
"\"\"\"(TS=(\"artificial intelligence\") OR TS=(\"machine learning\") OR TS=(\"neural network\") OR TS=(\"big data\") OR TS=(\"deep learning\")) AND (CU=PEOPLES R CHINA AND (CU=AUSTRIA OR CU=BELGIUM OR CU=BULGARIA OR CU=CROATIA OR CU=REPUBLIC OF CYPRUS OR CU=CZECH REPUBLIC OR CU=DENMARK OR CU=ESTONIA OR CU=FINLAND OR CU=FRANCE OR CU=GERMANY OR CU=GREECE OR CU=HUNGARY OR CU=IRELAND OR CU=ITALY OR CU=LATVIA OR CU=LITHUANIA OR CU=LUXEMBOURG OR CU=MALTA OR CU=NETHERLANDS OR CU=POLAND OR CU=PORTUGAL OR CU=ROMANIA OR CU=SLOVAKIA OR CU=SLOVENIA OR CU=SPAIN OR CU=SWEDEN))\"\"\""
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [
"other keywords: pattern recognition, computer vision, image classification, reinforcement learning, support vector machines, recommender system, random forest, ensemble models, image processing, generative network, ai ethic, natural language processing, clustering algorithm, feature extraction, time series forecast, anomaly detection, identity fraud detection, dimensionality reduction, feature elicitation, chatbot, clustering, unsupervised learning, supervised learning, convolutional network, adversarial network\n",
"\n",
"# AI ETHICS keyword!!!"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [
"# Only CPC classification? Or some basic PTC? (ASEAN analysis had some)"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": 1,
"outputs": [],
"source": [
"# Patent classes"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": 2,
"outputs": [],
"source": [
"# AI keywords PATSTAT and WOS"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "markdown",
"source": [
"# What I need\n",
"- List of visuals & tables / in a specified manner/ can be"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [
"# Baseline of co-publications\n",
"#\n",
"# Use address instead of CU?\n",
"# plus countries UK Norway Switzerland | Turkey Serbia"
],
"metadata": {
"collapsed": false
}
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 0
}