Machine learning models/Production/Czech Wikipedia article topic

Model card
Model card
This page is an on-wiki machine learning model card.
	A model card is a document about a machine learning model that seeks to answer basic questions about the model.
Model Information Hub
Model creator(s)	Aaron Halfaker (User:EpochFail) and Amir Sarabadani
Model owner(s)	WMF Machine Learning Team (ml@wikimediafoundation.org)
Model interface	Ores homepage
Code	drafttopic Github, ORES training data, and ORES model binaries
Uses PII	No
In production?	Yes
Which projects?	Czech Wikipedia
	This model uses article text to predict the likelihood that the article belongs to a set of topics.
	v; t; e;

Motivation[edit]

How can we predict what general topic an article is in? Answering this question is useful for various analyses of Wikipedia dynamics. However, it is difficult to group a very diverse range of Wikipedia articles into coherent, consistent topics manually.

This model, part of the ORES suite of models, analyzes an article to predict its likelihood of belonging to a set of topics. Similar models (though not necessarily with the same performance level or topics, are deployed across about a dozen other projects. There is also a language agnostic article topic model.

This model may be useful for high-level analyses of Wikipedia dynamics (pageviews, article quality, edit trends) and filtering articles.

Users and uses[edit]

Use this model for

high-level analyses of Wikipedia dynamics such as pageview, article quality, or edit trends — e.g. How are pageview dynamics different between the physics and biology categories?
filtering to relevant articles — e.g. filter articles only to those in the music category.

Don't use this model for

definitively establishing what topic an article pertains to
automated editing of articles or topics without a human in the loop

Current uses

This model is a part of ORES, and generally accessible via API. It is used for high-level analysis of Wikipedia, platform research, and other on-wiki tasks.

Example API call:

https://ores.wikimedia.org/v3/scores/cswiki/1234/articletopic

Ethical considerations, caveats, and recommendations[edit]

This model was trained on data that is now several years old (from mid-2020). Underlying data drift may skew model outputs.
This model uses word2vec as a training feature. Word2vec, like other natural language embeddings, encodes the linguistic biases of underlying datasets — along the lines of gender, race, ethnicity, religion etc. Since Wikipedia has known biases in its text, this model may encode and at times reproduce those biases.
This model has highly variable performance across different topics — consult the test statistics below to get a sense of inter-topic performance.

Model[edit]

Performance[edit]

Test data confusion matrix:

Test data confusion matrix

Label	n	True positive	False positive	False negative	True Negative
Culture.Biography.Biography*	16411	15081	1330	830	42956
Culture.Biography.Women	4309	3613	696	285	55603
Culture.Food and drink	1598	1140	458	116	58483
Culture.Internet culture	3175	2600	575	242	56780
Culture.Linguistics	1610	1149	461	86	58501
Culture.Literature	4968	3573	1395	516	54713
Culture.Media.Books	1697	1332	365	136	58364
Culture.Media.Entertainment	2268	1029	1239	307	57622
Culture.Media.Films	2531	2078	453	115	57551
Culture.Media.Media*	14349	12485	1864	1361	44487
Culture.Media.Music	3307	2782	525	261	56629
Culture.Media.Radio	425	198	227	41	59731
Culture.Media.Software	2392	1841	551	352	57453
Culture.Media.Television	2548	2167	381	121	57528
Culture.Media.Video games	1896	1727	169	49	58252
Culture.Performing arts	1520	960	560	134	58543
Culture.Philosophy and religion	4401	2479	1922	454	55342
Culture.Sports	5891	5267	624	191	54115
Culture.Visual arts.Architecture	2309	1650	659	240	57648
Culture.Visual arts.Comics and Anime	1679	1436	243	43	58475
Culture.Visual arts.Fashion	1059	702	357	83	59055
Culture.Visual arts.Visual arts*	5915	4343	1572	432	53850
Geography.Geographical	4652	3358	1294	725	54820
Geography.Regions.Africa.Africa*	4090	2581	1509	309	55798
Geography.Regions.Africa.Central Africa	732	332	400	74	59391
Geography.Regions.Africa.Eastern Africa	474	259	215	37	59686
Geography.Regions.Africa.Northern Africa	1558	938	620	122	58517
Geography.Regions.Africa.Southern Africa	675	312	363	59	59463
Geography.Regions.Africa.Western Africa	187	82	105	32	59978
Geography.Regions.Americas.Central America	1354	637	717	77	58766
Geography.Regions.Americas.North America	6020	3695	2325	981	53196
Geography.Regions.Americas.South America	1478	997	481	104	58615
Geography.Regions.Asia.Asia*	10847	8568	2279	888	48462
Geography.Regions.Asia.Central Asia	1311	813	498	117	58769
Geography.Regions.Asia.East Asia	2966	2257	709	188	57043
Geography.Regions.Asia.North Asia	1944	1268	676	292	57961
Geography.Regions.Asia.South Asia	1814	1327	487	96	58287
Geography.Regions.Asia.Southeast Asia	1603	925	678	88	58506
Geography.Regions.Asia.West Asia	2874	2191	683	175	57148
Geography.Regions.Europe.Eastern Europe	5252	3745	1507	665	54280
Geography.Regions.Europe.Europe*	16883	13054	3829	2544	40770
Geography.Regions.Europe.Northern Europe	4019	2435	1584	447	55731
Geography.Regions.Europe.Southern Europe	3488	2254	1234	338	56371
Geography.Regions.Europe.Western Europe	5209	3621	1588	641	54347
Geography.Regions.Oceania	1774	1198	576	87	58336
History and Society.Business and economics	3567	2068	1499	361	56269
History and Society.Education	1821	872	949	154	58222
History and Society.History	5592	3331	2261	695	53910
History and Society.Military and warfare	5797	4112	1685	591	53809
History and Society.Politics and government	4709	2502	2207	519	54969
History and Society.Society	6861	3083	3778	693	52643
History and Society.Transportation	4282	3865	417	165	55750
STEM.Biology	3828	3077	751	187	56182
STEM.Chemistry	1607	1290	317	147	58443
STEM.Computing	2851	2322	529	429	56917
STEM.Earth and environment	2224	1458	766	159	57814
STEM.Engineering	2978	2273	705	228	56991
STEM.Libraries & Information	717	467	250	57	59423
STEM.Mathematics	1208	937	271	77	58912
STEM.Medicine & Health	2098	1387	711	215	57884
STEM.Physics	1466	960	506	158	58573
STEM.STEM*	19061	16828	2233	1061	40075
STEM.Space	2057	1868	189	48	58092
STEM.Technology	5209	3765	1444	711	54277

Test data sample rates:

Test data sample rates

Label	Sample	Population
Culture.Biography.Biography*	0.273	0.123
Culture.Biography.Women	0.072	0.015
Culture.Food and drink	0.027	0.002
Culture.Internet culture	0.053	0.003
Culture.Linguistics	0.027	0.007
Culture.Literature	0.083	0.015
Culture.Media.Books	0.028	0.004
Culture.Media.Entertainment	0.038	0.004
Culture.Media.Films	0.042	0.011
Culture.Media.Media*	0.238	0.058
Culture.Media.Music	0.055	0.024
Culture.Media.Radio	0.007	0.002
Culture.Media.Software	0.04	0.001
Culture.Media.Television	0.042	0.009
Culture.Media.Video games	0.031	0.003
Culture.Performing arts	0.025	0.003
Culture.Philosophy and religion	0.073	0.011
Culture.Sports	0.098	0.071
Culture.Visual arts.Architecture	0.038	0.011
Culture.Visual arts.Comics and Anime	0.028	0.002
Culture.Visual arts.Fashion	0.018	0.001
Culture.Visual arts.Visual arts*	0.098	0.018
Geography.Geographical	0.077	0.024
Geography.Regions.Africa.Africa*	0.068	0.008
Geography.Regions.Africa.Central Africa	0.012	0.001
Geography.Regions.Africa.Eastern Africa	0.008	0
Geography.Regions.Africa.Northern Africa	0.026	0.001
Geography.Regions.Africa.Southern Africa	0.011	0.001
Geography.Regions.Africa.Western Africa	0.003	0.001
Geography.Regions.Americas.Central America	0.022	0.003
Geography.Regions.Americas.North America	0.1	0.064
Geography.Regions.Americas.South America	0.025	0.006
Geography.Regions.Asia.Asia*	0.18	0.045
Geography.Regions.Asia.Central Asia	0.022	0.001
Geography.Regions.Asia.East Asia	0.049	0.011
Geography.Regions.Asia.North Asia	0.032	0.001
Geography.Regions.Asia.South Asia	0.03	0.015
Geography.Regions.Asia.Southeast Asia	0.027	0.006
Geography.Regions.Asia.West Asia	0.048	0.011
Geography.Regions.Europe.Eastern Europe	0.087	0.013
Geography.Regions.Europe.Europe*	0.28	0.076
Geography.Regions.Europe.Northern Europe	0.067	0.031
Geography.Regions.Europe.Southern Europe	0.058	0.013
Geography.Regions.Europe.Western Europe	0.087	0.019
Geography.Regions.Oceania	0.029	0.015
History and Society.Business and economics	0.059	0.01
History and Society.Education	0.03	0.007
History and Society.History	0.093	0.011
History and Society.Military and warfare	0.096	0.014
History and Society.Politics and government	0.078	0.028
History and Society.Society	0.114	0.013
History and Society.Transportation	0.071	0.015
STEM.Biology	0.064	0.034
STEM.Chemistry	0.027	0.002
STEM.Computing	0.047	0.003
STEM.Earth and environment	0.037	0.005
STEM.Engineering	0.049	0.005
STEM.Libraries & Information	0.012	0.001
STEM.Mathematics	0.02	0
STEM.Medicine & Health	0.035	0.006
STEM.Physics	0.024	0.001
STEM.STEM*	0.317	0.069
STEM.Space	0.034	0.006
STEM.Technology	0.087	0.005

Test data performance:

Test data performance

Label	Match rate	Filter rate	Recall	Precision	f1	Accuracy	ROC AUC	PR AUC
Culture.Biography.Biography*	0.13	0.87	0.919	0.872	0.895	0.973	0.982	0.953
Culture.Biography.Women	0.017	0.983	0.838	0.708	0.768	0.993	0.983	0.781
Culture.Food and drink	0.004	0.996	0.713	0.471	0.567	0.997	0.979	0.603
Culture.Internet culture	0.007	0.993	0.819	0.404	0.541	0.995	0.984	0.726
Culture.Linguistics	0.007	0.993	0.714	0.782	0.746	0.996	0.976	0.74
Culture.Literature	0.02	0.98	0.719	0.548	0.622	0.986	0.974	0.667
Culture.Media.Books	0.005	0.995	0.785	0.577	0.665	0.997	0.982	0.689
Culture.Media.Entertainment	0.007	0.993	0.454	0.235	0.31	0.993	0.965	0.244
Culture.Media.Films	0.011	0.989	0.821	0.814	0.817	0.996	0.983	0.825
Culture.Media.Media*	0.079	0.921	0.87	0.645	0.741	0.964	0.978	0.854
Culture.Media.Music	0.025	0.975	0.841	0.818	0.829	0.992	0.984	0.849
Culture.Media.Radio	0.002	0.998	0.466	0.595	0.522	0.998	0.947	0.334
Culture.Media.Software	0.007	0.993	0.77	0.144	0.242	0.994	0.985	0.337
Culture.Media.Television	0.01	0.99	0.85	0.783	0.815	0.997	0.985	0.873
Culture.Media.Video games	0.003	0.997	0.911	0.739	0.816	0.999	0.99	0.904
Culture.Performing arts	0.004	0.996	0.632	0.445	0.522	0.997	0.976	0.516
Culture.Philosophy and religion	0.014	0.986	0.563	0.427	0.486	0.987	0.952	0.471
Culture.Sports	0.067	0.933	0.894	0.951	0.922	0.989	0.982	0.955
Culture.Visual arts.Architecture	0.012	0.988	0.715	0.648	0.68	0.993	0.98	0.68
Culture.Visual arts.Comics and Anime	0.003	0.997	0.855	0.719	0.781	0.999	0.988	0.793
Culture.Visual arts.Fashion	0.002	0.998	0.663	0.277	0.39	0.998	0.977	0.4
Culture.Visual arts.Visual arts*	0.021	0.979	0.734	0.632	0.679	0.987	0.973	0.74
Geography.Geographical	0.03	0.97	0.722	0.572	0.638	0.981	0.975	0.651
Geography.Regions.Africa.Africa*	0.01	0.99	0.631	0.474	0.541	0.992	0.968	0.537
Geography.Regions.Africa.Central Africa	0.002	0.998	0.454	0.187	0.265	0.998	0.973	0.15
Geography.Regions.Africa.Eastern Africa	0.001	0.999	0.546	0.286	0.376	0.999	0.961	0.219
Geography.Regions.Africa.Northern Africa	0.003	0.997	0.602	0.262	0.365	0.997	0.974	0.321
Geography.Regions.Africa.Southern Africa	0.002	0.998	0.462	0.354	0.401	0.998	0.948	0.215
Geography.Regions.Africa.Western Africa	0.001	0.999	0.439	0.36	0.395	0.999	0.909	0.194
Geography.Regions.Americas.Central America	0.003	0.997	0.47	0.543	0.504	0.997	0.963	0.473
Geography.Regions.Americas.North America	0.056	0.944	0.614	0.7	0.654	0.958	0.957	0.712
Geography.Regions.Americas.South America	0.006	0.994	0.675	0.707	0.691	0.996	0.973	0.693
Geography.Regions.Asia.Asia*	0.053	0.947	0.79	0.677	0.729	0.973	0.97	0.809
Geography.Regions.Asia.Central Asia	0.003	0.997	0.62	0.213	0.317	0.998	0.973	0.232
Geography.Regions.Asia.East Asia	0.012	0.988	0.761	0.728	0.744	0.994	0.98	0.791
Geography.Regions.Asia.North Asia	0.006	0.994	0.652	0.107	0.184	0.995	0.983	0.214
Geography.Regions.Asia.South Asia	0.013	0.987	0.732	0.873	0.796	0.994	0.97	0.816
Geography.Regions.Asia.Southeast Asia	0.005	0.995	0.577	0.699	0.632	0.996	0.968	0.587
Geography.Regions.Asia.West Asia	0.011	0.989	0.762	0.734	0.748	0.994	0.979	0.8
Geography.Regions.Europe.Eastern Europe	0.021	0.979	0.713	0.434	0.539	0.984	0.971	0.573
Geography.Regions.Europe.Europe*	0.113	0.887	0.773	0.52	0.622	0.928	0.946	0.687
Geography.Regions.Europe.Northern Europe	0.026	0.974	0.606	0.706	0.652	0.98	0.963	0.711
Geography.Regions.Europe.Southern Europe	0.014	0.986	0.646	0.589	0.616	0.99	0.97	0.643
Geography.Regions.Europe.Western Europe	0.025	0.975	0.695	0.538	0.607	0.983	0.97	0.63
Geography.Regions.Oceania	0.012	0.988	0.675	0.874	0.762	0.994	0.975	0.806
History and Society.Business and economics	0.012	0.988	0.58	0.481	0.526	0.989	0.962	0.507
History and Society.Education	0.006	0.994	0.479	0.574	0.522	0.994	0.963	0.494
History and Society.History	0.019	0.981	0.596	0.339	0.432	0.983	0.956	0.446
History and Society.Military and warfare	0.021	0.979	0.709	0.482	0.574	0.985	0.971	0.654
History and Society.Politics and government	0.024	0.976	0.531	0.622	0.573	0.978	0.95	0.596
History and Society.Society	0.018	0.982	0.449	0.306	0.364	0.98	0.917	0.325
History and Society.Transportation	0.017	0.983	0.903	0.824	0.862	0.996	0.987	0.912
STEM.Biology	0.03	0.97	0.804	0.894	0.846	0.99	0.979	0.898
STEM.Chemistry	0.004	0.996	0.803	0.333	0.471	0.997	0.987	0.418
STEM.Computing	0.01	0.99	0.814	0.227	0.355	0.992	0.986	0.367
STEM.Earth and environment	0.006	0.994	0.656	0.521	0.581	0.996	0.976	0.596
STEM.Engineering	0.008	0.992	0.763	0.502	0.606	0.995	0.98	0.71
STEM.Libraries & Information	0.001	0.999	0.651	0.297	0.408	0.999	0.968	0.385
STEM.Mathematics	0.002	0.998	0.776	0.199	0.316	0.999	0.983	0.494
STEM.Medicine & Health	0.008	0.992	0.661	0.535	0.591	0.994	0.974	0.599
STEM.Physics	0.003	0.997	0.655	0.171	0.272	0.997	0.981	0.24
STEM.STEM*	0.085	0.915	0.883	0.718	0.792	0.968	0.975	0.883
STEM.Space	0.006	0.994	0.908	0.869	0.888	0.999	0.993	0.951
STEM.Technology	0.017	0.983	0.723	0.224	0.342	0.986	0.974	0.479

Implementation[edit]

Model architecture

{
    "type": "GradientBoosting",
    "params": {
        "init": null,
        "population_rates": null,
        "max_depth": 5,
        "verbose": 0,
        "ccp_alpha": 0.0,
        "validation_fraction": 0.1,
        "warm_start": false,
        "loss": "deviance",
        "min_weight_fraction_leaf": 0.0,
        "max_leaf_nodes": null,
        "subsample": 1.0,
        "tol": 0.0001,
        "presort": "deprecated",
        "min_samples_split": 2,
        "random_state": null,
        "min_samples_leaf": 1,
        "center": false,
        "multilabel": true,
        "max_features": "log2",
        "learning_rate": 0.1,
        "n_estimators": 150,
        "min_impurity_split": null,
        "min_impurity_decrease": 0.0,
        "label_weights": {},
        "criterion": "friedman_mse",
        "labels": [
            "Culture.Biography.Biography*",
            "Culture.Biography.Women",
            "Culture.Food and drink",
            "Culture.Internet culture",
            "Culture.Linguistics",
            "Culture.Literature",
            "Culture.Media.Books",
            "Culture.Media.Entertainment",
            "Culture.Media.Films",
            "Culture.Media.Media*",
            "Culture.Media.Music",
            "Culture.Media.Radio",
            "Culture.Media.Software",
            "Culture.Media.Television",
            "Culture.Media.Video games",
            "Culture.Performing arts",
            "Culture.Philosophy and religion",
            "Culture.Sports",
            "Culture.Visual arts.Architecture",
            "Culture.Visual arts.Comics and Anime",
            "Culture.Visual arts.Fashion",
            "Culture.Visual arts.Visual arts*",
            "Geography.Geographical",
            "Geography.Regions.Africa.Africa*",
            "Geography.Regions.Africa.Central Africa",
            "Geography.Regions.Africa.Eastern Africa",
            "Geography.Regions.Africa.Northern Africa",
            "Geography.Regions.Africa.Southern Africa",
            "Geography.Regions.Africa.Western Africa",
            "Geography.Regions.Americas.Central America",
            "Geography.Regions.Americas.North America",
            "Geography.Regions.Americas.South America",
            "Geography.Regions.Asia.Asia*",
            "Geography.Regions.Asia.Central Asia",
            "Geography.Regions.Asia.East Asia",
            "Geography.Regions.Asia.North Asia",
            "Geography.Regions.Asia.South Asia",
            "Geography.Regions.Asia.Southeast Asia",
            "Geography.Regions.Asia.West Asia",
            "Geography.Regions.Europe.Eastern Europe",
            "Geography.Regions.Europe.Europe*",
            "Geography.Regions.Europe.Northern Europe",
            "Geography.Regions.Europe.Southern Europe",
            "Geography.Regions.Europe.Western Europe",
            "Geography.Regions.Oceania",
            "History and Society.Business and economics",
            "History and Society.Education",
            "History and Society.History",
            "History and Society.Military and warfare",
            "History and Society.Politics and government",
            "History and Society.Society",
            "History and Society.Transportation",
            "STEM.Biology",
            "STEM.Chemistry",
            "STEM.Computing",
            "STEM.Earth and environment",
            "STEM.Engineering",
            "STEM.Libraries & Information",
            "STEM.Mathematics",
            "STEM.Medicine & Health",
            "STEM.Physics",
            "STEM.STEM*",
            "STEM.Space",
            "STEM.Technology"
        ],
        "n_iter_no_change": null,
        "scale": false
    }
}

Output schema

{
    "title": "Scikit learn-based classifier score with probability",
    "properties": {
        "prediction": {
            "description": "The most likely labels predicted by the estimator",
            "items": {
                "type": "string"
            },
            "type": "array"
        },
        "probability": {
            "description": "A mapping of probabilities onto each of the potential output labels",
            "properties": {
                "Geography.Regions.Asia.Southeast Asia": {
                    "type": "number"
                },
                "Culture.Media.Media*": {
                    "type": "number"
                },
                "History and Society.Transportation": {
                    "type": "number"
                },
                "Geography.Regions.Asia.West Asia": {
                    "type": "number"
                },
                "Culture.Media.Radio": {
                    "type": "number"
                },
                "Geography.Regions.Americas.South America": {
                    "type": "number"
                },
                "Geography.Regions.Africa.Western Africa": {
                    "type": "number"
                },
                "Culture.Philosophy and religion": {
                    "type": "number"
                },
                "Geography.Regions.Europe.Eastern Europe": {
                    "type": "number"
                },
                "Geography.Regions.Asia.South Asia": {
                    "type": "number"
                },
                "STEM.Earth and environment": {
                    "type": "number"
                },
                "Geography.Regions.Africa.Central Africa": {
                    "type": "number"
                },
                "Culture.Food and drink": {
                    "type": "number"
                },
                "History and Society.Society": {
                    "type": "number"
                },
                "Culture.Media.Software": {
                    "type": "number"
                },
                "STEM.Chemistry": {
                    "type": "number"
                },
                "Culture.Media.Films": {
                    "type": "number"
                },
                "STEM.Space": {
                    "type": "number"
                },
                "STEM.Medicine & Health": {
                    "type": "number"
                },
                "Geography.Regions.Europe.Northern Europe": {
                    "type": "number"
                },
                "Culture.Media.Television": {
                    "type": "number"
                },
                "STEM.Biology": {
                    "type": "number"
                },
                "Geography.Regions.Asia.East Asia": {
                    "type": "number"
                },
                "Geography.Regions.Americas.North America": {
                    "type": "number"
                },
                "Culture.Media.Video games": {
                    "type": "number"
                },
                "Geography.Regions.Asia.Asia*": {
                    "type": "number"
                },
                "Culture.Visual arts.Fashion": {
                    "type": "number"
                },
                "Culture.Sports": {
                    "type": "number"
                },
                "Culture.Media.Books": {
                    "type": "number"
                },
                "History and Society.Business and economics": {
                    "type": "number"
                },
                "STEM.Physics": {
                    "type": "number"
                },
                "History and Society.Military and warfare": {
                    "type": "number"
                },
                "Culture.Internet culture": {
                    "type": "number"
                },
                "Geography.Regions.Europe.Europe*": {
                    "type": "number"
                },
                "Culture.Biography.Biography*": {
                    "type": "number"
                },
                "Geography.Regions.Asia.North Asia": {
                    "type": "number"
                },
                "Geography.Regions.Africa.Southern Africa": {
                    "type": "number"
                },
                "Geography.Regions.Africa.Eastern Africa": {
                    "type": "number"
                },
                "Geography.Regions.Americas.Central America": {
                    "type": "number"
                },
                "Culture.Visual arts.Architecture": {
                    "type": "number"
                },
                "Culture.Media.Entertainment": {
                    "type": "number"
                },
                "STEM.Mathematics": {
                    "type": "number"
                },
                "Culture.Biography.Women": {
                    "type": "number"
                },
                "Culture.Literature": {
                    "type": "number"
                },
                "STEM.Libraries & Information": {
                    "type": "number"
                },
                "Geography.Regions.Asia.Central Asia": {
                    "type": "number"
                },
                "STEM.STEM*": {
                    "type": "number"
                },
                "History and Society.History": {
                    "type": "number"
                },
                "Culture.Linguistics": {
                    "type": "number"
                },
                "Geography.Geographical": {
                    "type": "number"
                },
                "STEM.Computing": {
                    "type": "number"
                },
                "Geography.Regions.Africa.Northern Africa": {
                    "type": "number"
                },
                "Culture.Visual arts.Comics and Anime": {
                    "type": "number"
                },
                "History and Society.Education": {
                    "type": "number"
                },
                "Culture.Performing arts": {
                    "type": "number"
                },
                "Culture.Visual arts.Visual arts*": {
                    "type": "number"
                },
                "Geography.Regions.Europe.Western Europe": {
                    "type": "number"
                },
                "STEM.Engineering": {
                    "type": "number"
                },
                "Geography.Regions.Oceania": {
                    "type": "number"
                },
                "Culture.Media.Music": {
                    "type": "number"
                },
                "STEM.Technology": {
                    "type": "number"
                },
                "History and Society.Politics and government": {
                    "type": "number"
                },
                "Geography.Regions.Africa.Africa*": {
                    "type": "number"
                },
                "Geography.Regions.Europe.Southern Europe": {
                    "type": "number"
                }
            },
            "type": "object"
        }
    },
    "type": "object"
}

Example input and output

Input:

https://ores.wikimedia.org/v3/scores/cswiki/1234/articletopic

Output:

Example output

{
    "cswiki": {
        "models": {
            "articletopic": {
                "version": "1.3.0"
            }
        },
        "scores": {
            "1234": {
                "articletopic": {
                    "score": {
                        "prediction": [
                            "STEM.STEM*",
                            "STEM.Space"
                        ],
                        "probability": {
                            "Culture.Biography.Biography*": 0.0037581446757912217,
                            "Culture.Biography.Women": 0.0005751504978634069,
                            "Culture.Food and drink": 0.00013629102583591308,
                            "Culture.Internet culture": 0.00024705233108557957,
                            "Culture.Linguistics": 4.5023636851888105e-05,
                            "Culture.Literature": 0.000693481254355697,
                            "Culture.Media.Books": 0.0003302654788886533,
                            "Culture.Media.Entertainment": 0.0004557010040644442,
                            "Culture.Media.Films": 0.000745755840342992,
                            "Culture.Media.Media*": 0.0027738377186352623,
                            "Culture.Media.Music": 0.00017563847268040663,
                            "Culture.Media.Radio": 5.406588440219966e-05,
                            "Culture.Media.Software": 0.0008980023457288975,
                            "Culture.Media.Television": 0.000548303780375146,
                            "Culture.Media.Video games": 3.341663101629864e-05,
                            "Culture.Performing arts": 0.00010382012651605603,
                            "Culture.Philosophy and religion": 0.0018340714233612992,
                            "Culture.Sports": 0.0003340386603068036,
                            "Culture.Visual arts.Architecture": 0.0006493433462786338,
                            "Culture.Visual arts.Comics and Anime": 5.501988377413894e-05,
                            "Culture.Visual arts.Fashion": 0.00020240637526355807,
                            "Culture.Visual arts.Visual arts*": 0.0011734964014660275,
                            "Geography.Geographical": 0.003862913548780497,
                            "Geography.Regions.Africa.Africa*": 0.00283510137778092,
                            "Geography.Regions.Africa.Central Africa": 0.0007717336771633315,
                            "Geography.Regions.Africa.Eastern Africa": 5.4382462367102405e-05,
                            "Geography.Regions.Africa.Northern Africa": 0.0002468113306020045,
                            "Geography.Regions.Africa.Southern Africa": 0.005759778854208486,
                            "Geography.Regions.Africa.Western Africa": 4.758283244842901e-06,
                            "Geography.Regions.Americas.Central America": 0.0007230522994775956,
                            "Geography.Regions.Americas.North America": 0.008559027362312165,
                            "Geography.Regions.Americas.South America": 0.0010225938156441852,
                            "Geography.Regions.Asia.Asia*": 0.004625047209643945,
                            "Geography.Regions.Asia.Central Asia": 0.0005234422947221679,
                            "Geography.Regions.Asia.East Asia": 0.0036567708976141464,
                            "Geography.Regions.Asia.North Asia": 0.004117880625705837,
                            "Geography.Regions.Asia.South Asia": 0.001231314226046212,
                            "Geography.Regions.Asia.Southeast Asia": 0.0008340922220495317,
                            "Geography.Regions.Asia.West Asia": 0.0003554093910782288,
                            "Geography.Regions.Europe.Eastern Europe": 0.0065926663899134414,
                            "Geography.Regions.Europe.Europe*": 0.013979080013835353,
                            "Geography.Regions.Europe.Northern Europe": 0.00154029611316488,
                            "Geography.Regions.Europe.Southern Europe": 0.00068486964155431,
                            "Geography.Regions.Europe.Western Europe": 0.0027471763060663364,
                            "Geography.Regions.Oceania": 0.0003717339481496353,
                            "History and Society.Business and economics": 0.002207248293968202,
                            "History and Society.Education": 0.0004226747257376408,
                            "History and Society.History": 0.003777251589564783,
                            "History and Society.Military and warfare": 0.0047491280843299875,
                            "History and Society.Politics and government": 0.005142941696595345,
                            "History and Society.Society": 0.033398761452264884,
                            "History and Society.Transportation": 0.11443321001987419,
                            "STEM.Biology": 0.002447465453906354,
                            "STEM.Chemistry": 0.005747175118744066,
                            "STEM.Computing": 0.00045352819823348217,
                            "STEM.Earth and environment": 0.0033121889091357634,
                            "STEM.Engineering": 0.004281775261544969,
                            "STEM.Libraries & Information": 7.468451141451151e-05,
                            "STEM.Mathematics": 4.996334970267717e-05,
                            "STEM.Medicine & Health": 0.0007865993537385966,
                            "STEM.Physics": 0.29800230259682176,
                            "STEM.STEM*": 0.9983754315472244,
                            "STEM.Space": 0.996157360237683,
                            "STEM.Technology": 0.14559689671134318
                        }
                    }
                }
            }
        }
    }
}

Data[edit]

Data pipeline

The data to train was fetched from a set of revision IDs. Then various pieces of information about the revision were extracted using automated processes, and the revision text was fed into word2vec to get an article embedding. Finally, labels are derived from the mid-level WikiProject categories that the article is associated with.

Training data

Training data was automatically and randomly separated from test data during training using the drafttopic git repository (which trains both drafttopic and articletopic models).

Test data

Test data was automatically and randomly split off from train data using the drafttopic git repository (which trains both drafttopic and articletopic models). The model then makes a prediction on that data, which is compared to the underlying ground truth to calculate performance statistics.

Licenses[edit]

Code: MIT license
Model: MIT license

Citation[edit]

Cite this model card as:

@misc{
  Triedman_Bazira_2023_Czech_Wikipedia_article_topic,
  title={ Czech Wikipedia article topic model card },
  author={ Triedman, Harold and Bazira, Kevin },
  year={ 2023 },
  url={ https://meta.wikimedia.org/wiki/Machine_learning_models/Production/Czech_Wikipedia_article_topic }
}