initial commit

.babelrc

@@ -0,0 +1,3 @@
+{
+  "presets": ["@babel/preset-env"]
+}

.eslintrc.js

@@ -0,0 +1,42 @@
+module.exports = {
+  'env': {
+    'node': true,
+    'commonjs': true,
+    'es6': true
+  },
+  'extends': 'eslint:recommended',
+  'parserOptions': {
+    'ecmaVersion': 2018,
+    'sourceType': 'module',
+  },
+  'rules': {
+    'indent': [
+      'warn',
+      2,
+      {
+        'VariableDeclarator': {'var': 2, 'let': 2, 'const': 3},
+        'SwitchCase': 1,
+        'MemberExpression': 1,
+        'CallExpression': {'arguments': 'first'},
+        'ArrayExpression': 'first',
+        'ObjectExpression': 'first',
+        'ignoredNodes': ['ConditionalExpression']
+      },
+    ],
+    'quotes': [
+      'warn',
+      'single'
+    ],
+    'semi': [
+      'warn',
+      'always'
+    ],
+    'no-console': [
+      'warn',
+      { 'allow': ['warn', 'error'] }
+    ],
+    'no-trailing-spaces': [
+      'warn'
+    ]
+  }
+};

.gitignore

@@ -0,0 +1,99 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# TypeScript v1 declaration files
+typings/
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variables file
+.env
+.env.test
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+
+# next.js build output
+.next
+
+# nuxt.js build output
+.nuxt
+
+# vuepress build output
+.vuepress/dist
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+/.project
+/.settings
+/benchmarks.json
+/benchmarks.txt
+/dist
+
+# remote sync config file
+.remote-sync.json
+
+# Output
+/cache*
+/dataset*
+/charts*
+/experiments*
+/wikipedia-dump*
+/eval*

LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2022 Friedrich Schiller University Jena
+Copyright (c) 2022 German Aerospace Center (DLR)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,118 @@
+[![DOI](https://zenodo.org/badge/.svg)](https://zenodo.org/badge/latestdoi/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://github.com/fusion-jena/wiki-category-consistency/blob/master/LICENSE)
+
+# Consistency between Wikidata and Wikipedia Categories
+
+- We perform an analysis of consistencies between [Wikipedia category](https://en.wikipedia.org/wiki/Wikipedia:Categorization) members and their Wikidata counterpart entities retrieved by executing the SPARQL queries attached to the Wikidata categories under the property [Wikidata SPARQL query equivalent](https://www.wikidata.org/wiki/Property:P3921).
+- We focus on comparing the member sets of the two sources, and automatically investigating possible reasons making them not identical, in addition to a comparison of the consistency of the information provided within the Wikidata category itself.
+- For that, we propose a pipeline for the generation and evaluation of relevant data (categories and Wikidata/Wikipedia entities sets).
+- Wikipedia category members are retrieved by traversing the Wikipedia category hierarchy in all available languages.
+- This repository provides the steps needed to either reproduce the current results or conduct a new experiment using other Wikipedia/Wikidata versions.
+- The pipeline works using both Wikipedia/Wikidata public endpoints and SQL/JSON dumps.
+- Our experiments were run using **the Wikidata JSON dump of 2022-05-02 and the Wikipedia SQL dumps of 2022-05-01**.
+
+# Candidate Generation and Evaluation
+
+![approach!](figs/approach.png)
+
+- The figure above depicts the workflow for data generation and evaluation (see paper for more details).
+
+## Cache Population
+
+- We provide two options to run the generation workflow:
+
+### From Dumps
+
+1. First, two kind of dump versions should be selected:
+  - [Wikidata JSON Dump](https://dumps.wikimedia.org/wikidatawiki/entities/) (`wikidata-<version>-all.json.gz`)
+  - [Wikipedia SQL Dumps](https://dumps.wikimedia.org/backup-index.html) (available dataset versions could be checked by visiting e.g., [enwiki](https://dumps.wikimedia.org/enwiki/) for English Wikipedia)
+
+2. Second, Setup a MariaDB database (place where Wikipedia SQL Dumps will be imported)
+  - Install MariaDB : `sudo apt-get install mariadb-server`.
+  - Set root password:
+    ```
+    $ sudo mysql -u root
+    MariaDB [(none)]> SET PASSWORD = PASSWORD('DB_PASSWORD');
+    MariaDB [(none)]> update mysql.user set plugin = 'mysql_native_password' where User='root';
+    MariaDB [(none)]> FLUSH PRIVILEGES;
+    ```
+  - Create a Database:
+    ```
+    $ sudo mysql -u root
+    MariaDB [(none)]> create database <DB_NAME> character set binary;
+    Query OK, 1 row affected (0.00 sec)
+
+    MariaDB [(none)]> use <DB_NAME>;
+    Database changed
+    ```
+  - Optimize Database import by setting following parameter in `/etc/mysql/my.cnf` and then restart the database server `service mysql restart`.
+  ```
+  wait_timeout = 604800
+  innodb_buffer_pool_size = 8G
+  innodb_log_buffer_size = 1G
+  innodb_log_file_size = 512M
+  innodb_flush_log_at_trx_commit = 2
+  innodb_doublewrite = 0
+  innodb_write_io_threads = 16
+  ```
+3. Update [configuration file](https://github.com/fusion-jena/wiki-category-consistency/blob/master/src/cache-population/config.js) in `./src/cache-population/config.js`
+  ```
+  // wikidata dump version
+  wdDump: path.join(__dirname,'..', '..', '..', 'wikidata-<version>-all.json.gz'),
+  // wikipedia dump version
+  dumpDate : <wikipedia-version>,
+  // wikipedia database user
+  user: 'root',
+  // wikipedia database password
+  password: <DB_PASSWORD>,
+  // wikipedia database name
+  databaseName: <DB_NAME>,
+  ```
+4. Install [Node.js (minimum v14.16.1)](https://nodejs.org/en/)
+5. First download the repository and install dependencies: run `npm install` in the project root folder.
+6. Populate caches from dumps : `npm run runner`
+7. Continue with the steps described under [Candidate Generation and Cleaning](#candidate-generation-and-cleaning)
+
+### From Endpoints
+
+- This option does not need local setup or prior cache population.
+- It allows to directly send requests to Wikidata/Wikipedia public endpoints:
+	- [Wikidata public endpoint](https://query.wikidata.org/sparql)
+	- [MediaWiki API](https://www.mediawiki.org/wiki/API:Main_page)
+- To generate relevant data from endpoints, the steps under [Candidate Generation and Cleaning](#candidate-generation-and-cleaning) can directly be followed.
+
+## Candidate Generation and Cleaning
+
+- **To reproduce the current experiments**, one can make use of the already filled caches provided on Zenodo: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.6913134.svg)](https://doi.org/10.5281/zenodo.6913134).
+	- A collection of SQLite database files containing all data retrieved from the Wikidata JSON dump of 2022-05-02 and the Wikipedia SQL dumps of 2022-05-01.
+
+- To reproduce current experiments or perform new ones, the steps below should be followed (start directly with step 3 if Node.js and dependencies were already installed in [From Dumps](#from-dumps)):
+
+1. Install [Node.js (minimum v14.16.1)](https://nodejs.org/en/)
+2. First download the repository and install dependencies: run `npm install` in the project root folder.
+3.  
+  * *Generate from Endpoints* : setup `endpointEnabled: true` in `./src/config/config.js`.
+  * *Generate from Dumps* : setup `endpointEnabled: false` in `./src/config/config.js`.
+  * *Reproduce current experiments* : setup `endpointEnabled: false` in `./src/config/config.js`. In the root folder create a folder `./cache/`, unzip `wiki-category-consistency-cache.zip` and copy the content of the underlying folder (cache) in the newly created `cache` folder.
+4. To generate candidate categories run `npm run generateCandidate` in the root folder. The output files can be found under `./dataset/` . The output is a JSON file containing all needed raw data needed for further processing: `./dataset/raw-data.json`, in addition to log and statistics files.
+5. Next, for candidate cleaning, run `npm run cleanCandidate` in the root folder. The output is a JSON file with selected category entries: `./dataset/finalData.json` together with statistics file.
+
+- The output of the candidate generation and cleaning steps using the Wikidata JSON dump of 2022-05-02 and the Wikipedia SQL dumps of 2022-05-01 (`./dataset/raw-data.json`, `./dataset/finalData.json`, and accompanying files) are provided on Zenodo: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.6913282.svg)](https://doi.org/10.5281/zenodo.6913282).
+
+## Evaluation
+
+- The evaluation takes as input the file with cleaned category entries `./dataset/finalData.json`.
+
+1. Generate the needed evaluation metrics by running `npm run compareSPARQL` in the root folder. The output is a JSON file `./eval/compare.json` together with an additional statistics file.
+2. Plot the charts by running `npm run generatePlots` in the root folder. The output is a collection of html files under the folder `./charts/`.
+
+- Experiment results (`./eval/compare.json` with a statistics file) using the previously mentioned dump versions, are provided on Zenodo: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.6913332.svg)](https://doi.org/10.5281/zenodo.6913332).
+
+
+<!---## Cite , consider updating codemeta with paper link and also zenodo metadata-->
+
+## License
+
+This project is licensed under the [MIT License](https://git.rz.uni-jena.de/fusion/project/dlr-knowledge-modeling/wiki-category-consistency/-/blob/master/LICENSE).
+
+

codemeta.json

@@ -0,0 +1,62 @@
+{
+    "@context": "https://doi.org/10.5063/schema/codemeta-2.0",
+    "@type": "SoftwareSourceCode",
+    "license": "https://spdx.org/licenses/MIT",
+    "codeRepository": "",
+    "dateCreated": "",
+    "datePublished": "",
+    "dateModified": "",
+    "downloadUrl": "",
+    "issueTracker": "",
+    "name": "wiki-category-consistency",
+    "version": "1.0.0",
+    "identifier": "",
+    "description": "Source code for Evaluating the consistency between Wikipedia and Wikidata categories",
+    "referencePublication": "",
+    "keywords": [
+        "Wikidata",
+        "Wikipedia"
+    ],
+    "programmingLanguage": [
+        "JavaScript"
+    ],
+    "runtimePlatform": [
+        "nodejs"
+    ],
+    "softwareRequirements": [
+        "node version >= v14.16.1"
+    ],
+    "relatedLink": [
+		"https://doi.org/10.5281/zenodo.6913134",
+		"https://doi.org/10.5281/zenodo.6913282",
+		"https://doi.org/10.5281/zenodo.6913332"
+
+
+    ],
+    "author": [
+        {
+            "@type": "Person",
+            "@id": "https://orcid.org/0000-0001-8896-8208",
+            "givenName": "Leila",
+            "familyName": "Feddoul",
+            "email": "[email protected]",
+            "affiliation": {
+                "@type": "Organization",
+                "name": "Heinz Nixdorf Chair for Distributed Information Systems, Friedrich Schiller University Jena, Jena, Germany"
+            }
+        }
+    ],
+    "contributor": [
+        {
+            "@type": "Person",
+            "@id": "https://orcid.org/0000-0002-0964-4457",
+            "givenName": "Sirko",
+            "familyName": "Schindler",
+            "email": "[email protected]",
+            "affiliation": {
+                "@type": "Organization",
+                "name": "Institute of Data Science, German Aerospace Center DLR, Jena, Germany"
+            }
+        }
+    ]
+}