Machine learning models/Production/Vietnamese 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?	Vietnamese 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/viwiki/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*	14139	12651	1488	789	45836
Culture.Biography.Women	5153	4127	1026	774	54837
Culture.Food and drink	1399	1015	384	122	59243
Culture.Internet culture	3531	2917	614	233	57000
Culture.Linguistics	1509	1165	344	69	59186
Culture.Literature	5659	4444	1215	505	54600
Culture.Media.Books	1467	1089	378	111	59186
Culture.Media.Entertainment	1984	1041	943	194	58586
Culture.Media.Films	2612	2073	539	173	57979
Culture.Media.Media*	13270	11633	1637	1282	46212
Culture.Media.Music	2908	2509	399	163	57693
Culture.Media.Radio	285	178	107	32	60447
Culture.Media.Software	2291	1910	381	288	58185
Culture.Media.Television	1983	1438	545	133	58648
Culture.Media.Video games	2139	1969	170	54	58571
Culture.Performing arts	1374	960	414	105	59285
Culture.Philosophy and religion	3040	1731	1309	295	57429
Culture.Sports	3871	3411	460	104	56789
Culture.Visual arts.Architecture	1854	1334	520	167	58743
Culture.Visual arts.Comics and Anime	2239	2029	210	78	58447
Culture.Visual arts.Fashion	1501	1213	288	105	59158
Culture.Visual arts.Visual arts*	6119	4741	1378	400	54245
Geography.Geographical	3991	2584	1407	552	56221
Geography.Regions.Africa.Africa*	5744	4467	1277	485	54535
Geography.Regions.Africa.Central Africa	1214	811	403	123	59427
Geography.Regions.Africa.Eastern Africa	451	216	235	40	60273
Geography.Regions.Africa.Northern Africa	1474	1036	438	95	59195
Geography.Regions.Africa.Southern Africa	1178	798	380	78	59508
Geography.Regions.Africa.Western Africa	672	537	135	41	60051
Geography.Regions.Americas.Central America	1588	992	596	116	59060
Geography.Regions.Americas.North America	5438	3677	1761	651	54675
Geography.Regions.Americas.South America	2210	1706	504	183	58371
Geography.Regions.Asia.Asia*	13867	11650	2217	1216	45681
Geography.Regions.Asia.Central Asia	1211	914	297	84	59469
Geography.Regions.Asia.East Asia	5571	4489	1082	445	54748
Geography.Regions.Asia.North Asia	1693	1283	410	235	58836
Geography.Regions.Asia.South Asia	2038	1624	414	108	58618
Geography.Regions.Asia.Southeast Asia	2632	1945	687	190	57942
Geography.Regions.Asia.West Asia	2178	1753	425	105	58481
Geography.Regions.Europe.Eastern Europe	3590	2868	722	277	56897
Geography.Regions.Europe.Europe*	12682	10215	2467	1220	46862
Geography.Regions.Europe.Northern Europe	2896	1842	1054	227	57641
Geography.Regions.Europe.Southern Europe	2854	2126	728	203	57707
Geography.Regions.Europe.Western Europe	4043	3153	890	237	56484
Geography.Regions.Oceania	2238	1660	578	126	58400
History and Society.Business and economics	3404	2099	1305	350	57010
History and Society.Education	1589	926	663	132	59043
History and Society.History	4595	2468	2127	569	55600
History and Society.Military and warfare	5048	3942	1106	446	55270
History and Society.Politics and government	4595	2624	1971	485	55684
History and Society.Society	6148	2979	3169	513	54103
History and Society.Transportation	3573	3290	283	82	57109
STEM.Biology	7137	6573	564	165	53462
STEM.Chemistry	1506	1175	331	170	59088
STEM.Computing	2452	2053	399	305	58007
STEM.Earth and environment	1649	1118	531	123	58992
STEM.Engineering	3027	2529	498	129	57608
STEM.Libraries & Information	489	359	130	32	60243
STEM.Mathematics	942	782	160	56	59766
STEM.Medicine & Health	1774	1261	513	144	58846
STEM.Physics	1374	1025	349	139	59251
STEM.STEM*	20595	18875	1720	892	39277
STEM.Space	1637	1485	152	39	59088
STEM.Technology	4233	3133	1100	585	55946

Test data sample rates:

Test data sample rates

Label	Sample	Population
Culture.Biography.Biography*	0.233	0.123
Culture.Biography.Women	0.085	0.015
Culture.Food and drink	0.023	0.002
Culture.Internet culture	0.058	0.003
Culture.Linguistics	0.025	0.007
Culture.Literature	0.093	0.015
Culture.Media.Books	0.024	0.004
Culture.Media.Entertainment	0.033	0.004
Culture.Media.Films	0.043	0.011
Culture.Media.Media*	0.218	0.058
Culture.Media.Music	0.048	0.024
Culture.Media.Radio	0.005	0.002
Culture.Media.Software	0.038	0.001
Culture.Media.Television	0.033	0.009
Culture.Media.Video games	0.035	0.003
Culture.Performing arts	0.023	0.003
Culture.Philosophy and religion	0.05	0.011
Culture.Sports	0.064	0.071
Culture.Visual arts.Architecture	0.031	0.011
Culture.Visual arts.Comics and Anime	0.037	0.002
Culture.Visual arts.Fashion	0.025	0.001
Culture.Visual arts.Visual arts*	0.101	0.018
Geography.Geographical	0.066	0.024
Geography.Regions.Africa.Africa*	0.095	0.008
Geography.Regions.Africa.Central Africa	0.02	0.001
Geography.Regions.Africa.Eastern Africa	0.007	0
Geography.Regions.Africa.Northern Africa	0.024	0.001
Geography.Regions.Africa.Southern Africa	0.019	0.001
Geography.Regions.Africa.Western Africa	0.011	0.001
Geography.Regions.Americas.Central America	0.026	0.003
Geography.Regions.Americas.North America	0.089	0.064
Geography.Regions.Americas.South America	0.036	0.006
Geography.Regions.Asia.Asia*	0.228	0.045
Geography.Regions.Asia.Central Asia	0.02	0.001
Geography.Regions.Asia.East Asia	0.092	0.011
Geography.Regions.Asia.North Asia	0.028	0.001
Geography.Regions.Asia.South Asia	0.034	0.015
Geography.Regions.Asia.Southeast Asia	0.043	0.006
Geography.Regions.Asia.West Asia	0.036	0.011
Geography.Regions.Europe.Eastern Europe	0.059	0.013
Geography.Regions.Europe.Europe*	0.209	0.076
Geography.Regions.Europe.Northern Europe	0.048	0.031
Geography.Regions.Europe.Southern Europe	0.047	0.013
Geography.Regions.Europe.Western Europe	0.067	0.019
Geography.Regions.Oceania	0.037	0.015
History and Society.Business and economics	0.056	0.01
History and Society.Education	0.026	0.007
History and Society.History	0.076	0.011
History and Society.Military and warfare	0.083	0.014
History and Society.Politics and government	0.076	0.028
History and Society.Society	0.101	0.013
History and Society.Transportation	0.059	0.015
STEM.Biology	0.117	0.034
STEM.Chemistry	0.025	0.002
STEM.Computing	0.04	0.003
STEM.Earth and environment	0.027	0.005
STEM.Engineering	0.05	0.005
STEM.Libraries & Information	0.008	0.001
STEM.Mathematics	0.016	0
STEM.Medicine & Health	0.029	0.006
STEM.Physics	0.023	0.001
STEM.STEM*	0.339	0.069
STEM.Space	0.027	0.006
STEM.Technology	0.07	0.005

Test data performance:

Test data performance

Label	Match rate	Filter rate	Recall	Precision	f1	Accuracy	ROC AUC	PR AUC
Culture.Biography.Biography*	0.125	0.875	0.895	0.881	0.888	0.972	0.981	0.945
Culture.Biography.Women	0.025	0.975	0.801	0.459	0.584	0.983	0.983	0.57
Culture.Food and drink	0.004	0.996	0.726	0.466	0.567	0.997	0.982	0.594
Culture.Internet culture	0.007	0.993	0.826	0.416	0.553	0.995	0.987	0.736
Culture.Linguistics	0.007	0.993	0.772	0.83	0.8	0.997	0.978	0.821
Culture.Literature	0.021	0.979	0.785	0.574	0.663	0.988	0.98	0.727
Culture.Media.Books	0.005	0.995	0.742	0.616	0.673	0.997	0.985	0.708
Culture.Media.Entertainment	0.005	0.995	0.525	0.364	0.43	0.995	0.97	0.415
Culture.Media.Films	0.011	0.989	0.794	0.739	0.765	0.995	0.984	0.812
Culture.Media.Media*	0.077	0.923	0.877	0.669	0.759	0.967	0.981	0.85
Culture.Media.Music	0.023	0.977	0.863	0.882	0.872	0.994	0.986	0.913
Culture.Media.Radio	0.002	0.998	0.625	0.718	0.668	0.999	0.946	0.506
Culture.Media.Software	0.006	0.994	0.834	0.184	0.301	0.995	0.987	0.359
Culture.Media.Television	0.009	0.991	0.725	0.74	0.733	0.995	0.982	0.737
Culture.Media.Video games	0.003	0.997	0.921	0.723	0.81	0.999	0.992	0.913
Culture.Performing arts	0.004	0.996	0.699	0.534	0.605	0.997	0.98	0.594
Culture.Philosophy and religion	0.011	0.989	0.569	0.545	0.557	0.99	0.962	0.561
Culture.Sports	0.064	0.936	0.881	0.974	0.925	0.99	0.982	0.959
Culture.Visual arts.Architecture	0.01	0.99	0.72	0.73	0.725	0.994	0.981	0.717
Culture.Visual arts.Comics and Anime	0.003	0.997	0.906	0.599	0.722	0.998	0.989	0.805
Culture.Visual arts.Fashion	0.002	0.998	0.808	0.27	0.404	0.998	0.987	0.346
Culture.Visual arts.Visual arts*	0.021	0.979	0.775	0.664	0.715	0.989	0.977	0.764
Geography.Geographical	0.025	0.975	0.647	0.617	0.632	0.982	0.97	0.679
Geography.Regions.Africa.Africa*	0.015	0.985	0.778	0.409	0.536	0.99	0.978	0.611
Geography.Regions.Africa.Central Africa	0.002	0.998	0.668	0.17	0.271	0.998	0.983	0.243
Geography.Regions.Africa.Eastern Africa	0.001	0.999	0.479	0.247	0.326	0.999	0.966	0.139
Geography.Regions.Africa.Northern Africa	0.002	0.998	0.703	0.35	0.467	0.998	0.98	0.37
Geography.Regions.Africa.Southern Africa	0.002	0.998	0.677	0.378	0.486	0.998	0.974	0.354
Geography.Regions.Africa.Western Africa	0.001	0.999	0.799	0.445	0.571	0.999	0.982	0.49
Geography.Regions.Americas.Central America	0.004	0.996	0.625	0.513	0.564	0.997	0.975	0.549
Geography.Regions.Americas.North America	0.054	0.946	0.676	0.798	0.732	0.968	0.968	0.807
Geography.Regions.Americas.South America	0.008	0.992	0.772	0.611	0.682	0.995	0.982	0.64
Geography.Regions.Asia.Asia*	0.063	0.937	0.84	0.607	0.705	0.968	0.974	0.79
Geography.Regions.Asia.Central Asia	0.002	0.998	0.755	0.317	0.446	0.998	0.985	0.405
Geography.Regions.Asia.East Asia	0.017	0.983	0.806	0.536	0.644	0.99	0.981	0.668
Geography.Regions.Asia.North Asia	0.005	0.995	0.758	0.15	0.25	0.996	0.983	0.23
Geography.Regions.Asia.South Asia	0.014	0.986	0.797	0.87	0.832	0.995	0.982	0.869
Geography.Regions.Asia.Southeast Asia	0.008	0.992	0.739	0.577	0.648	0.995	0.979	0.688
Geography.Regions.Asia.West Asia	0.011	0.989	0.805	0.832	0.818	0.996	0.981	0.839
Geography.Regions.Europe.Eastern Europe	0.015	0.985	0.799	0.682	0.736	0.993	0.983	0.815
Geography.Regions.Europe.Europe*	0.085	0.915	0.805	0.724	0.762	0.962	0.969	0.832
Geography.Regions.Europe.Northern Europe	0.023	0.977	0.636	0.836	0.723	0.985	0.971	0.782
Geography.Regions.Europe.Southern Europe	0.013	0.987	0.745	0.737	0.741	0.993	0.978	0.801
Geography.Regions.Europe.Western Europe	0.019	0.981	0.78	0.785	0.782	0.992	0.98	0.817
Geography.Regions.Oceania	0.013	0.987	0.742	0.841	0.788	0.994	0.98	0.826
History and Society.Business and economics	0.012	0.988	0.617	0.507	0.557	0.99	0.971	0.56
History and Society.Education	0.007	0.993	0.583	0.659	0.619	0.995	0.973	0.613
History and Society.History	0.016	0.984	0.537	0.367	0.436	0.985	0.957	0.443
History and Society.Military and warfare	0.019	0.981	0.781	0.582	0.667	0.989	0.98	0.759
History and Society.Politics and government	0.024	0.976	0.571	0.657	0.611	0.98	0.956	0.647
History and Society.Society	0.015	0.985	0.485	0.397	0.437	0.984	0.94	0.408
History and Society.Transportation	0.015	0.985	0.921	0.908	0.914	0.997	0.989	0.943
STEM.Biology	0.034	0.966	0.921	0.912	0.917	0.994	0.987	0.959
STEM.Chemistry	0.004	0.996	0.78	0.298	0.431	0.997	0.987	0.48
STEM.Computing	0.007	0.993	0.837	0.302	0.443	0.994	0.988	0.475
STEM.Earth and environment	0.005	0.995	0.678	0.598	0.635	0.996	0.977	0.623
STEM.Engineering	0.007	0.993	0.835	0.663	0.739	0.997	0.985	0.847
STEM.Libraries & Information	0.001	0.999	0.734	0.462	0.567	0.999	0.972	0.53
STEM.Mathematics	0.001	0.999	0.83	0.27	0.407	0.999	0.984	0.51
STEM.Medicine & Health	0.007	0.993	0.711	0.652	0.68	0.996	0.974	0.718
STEM.Physics	0.003	0.997	0.746	0.213	0.332	0.997	0.986	0.322
STEM.STEM*	0.084	0.916	0.916	0.754	0.827	0.974	0.981	0.908
STEM.Space	0.006	0.994	0.907	0.893	0.9	0.999	0.994	0.952
STEM.Technology	0.014	0.986	0.74	0.269	0.395	0.988	0.977	0.446

Implementation[edit]

Model architecture

{
    "type": "GradientBoosting",
    "params": {
        "scale": false,
        "center": false,
        "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"
        ],
        "multilabel": true,
        "population_rates": null,
        "ccp_alpha": 0.0,
        "criterion": "friedman_mse",
        "init": null,
        "learning_rate": 0.1,
        "loss": "deviance",
        "max_depth": 5,
        "max_features": "log2",
        "max_leaf_nodes": null,
        "min_impurity_decrease": 0.0,
        "min_impurity_split": null,
        "min_samples_leaf": 1,
        "min_samples_split": 2,
        "min_weight_fraction_leaf": 0.0,
        "n_estimators": 150,
        "n_iter_no_change": null,
        "presort": "deprecated",
        "random_state": null,
        "subsample": 1.0,
        "tol": 0.0001,
        "validation_fraction": 0.1,
        "verbose": 0,
        "warm_start": false,
        "label_weights": {}
    }
}

Output schema

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

Example input and output

Input:

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

Output:

Example output

{
    "viwiki": {
        "models": {
            "articletopic": {
                "version": "1.4.0"
            }
        },
        "scores": {
            "1234": {
                "articletopic": {
                    "score": {
                        "prediction": [
                            "Culture.Linguistics",
                            "Geography.Geographical",
                            "Geography.Regions.Africa.Africa*",
                            "STEM.STEM*"
                        ],
                        "probability": {
                            "Culture.Biography.Biography*": 0.010688680396213181,
                            "Culture.Biography.Women": 0.008195720460488087,
                            "Culture.Food and drink": 0.00012907532555688536,
                            "Culture.Internet culture": 0.013800940060468312,
                            "Culture.Linguistics": 0.5191168929941612,
                            "Culture.Literature": 0.0025178108493059317,
                            "Culture.Media.Books": 0.000812132490359537,
                            "Culture.Media.Entertainment": 0.0006821999958547265,
                            "Culture.Media.Films": 0.030271891185779207,
                            "Culture.Media.Media*": 0.008323998748143888,
                            "Culture.Media.Music": 0.0002453251096654214,
                            "Culture.Media.Radio": 0.0022820146632477724,
                            "Culture.Media.Software": 0.004399225981860488,
                            "Culture.Media.Television": 0.0006043194680847222,
                            "Culture.Media.Video games": 0.00012009680849040888,
                            "Culture.Performing arts": 0.0004276073083262229,
                            "Culture.Philosophy and religion": 0.0006390607811047581,
                            "Culture.Sports": 0.16329437697514143,
                            "Culture.Visual arts.Architecture": 0.0001462376454522797,
                            "Culture.Visual arts.Comics and Anime": 5.139459619313559e-05,
                            "Culture.Visual arts.Fashion": 0.00010666140674559313,
                            "Culture.Visual arts.Visual arts*": 0.004025427327690172,
                            "Geography.Geographical": 0.9997938301645891,
                            "Geography.Regions.Africa.Africa*": 0.9745448423349992,
                            "Geography.Regions.Africa.Central Africa": 0.0027669019697055064,
                            "Geography.Regions.Africa.Eastern Africa": 0.0012268282092543052,
                            "Geography.Regions.Africa.Northern Africa": 0.0009715033768551983,
                            "Geography.Regions.Africa.Southern Africa": 0.08328049473179015,
                            "Geography.Regions.Africa.Western Africa": 0.010382244078188742,
                            "Geography.Regions.Americas.Central America": 0.0008457881065380281,
                            "Geography.Regions.Americas.North America": 0.0022683028023005257,
                            "Geography.Regions.Americas.South America": 0.004731186807992782,
                            "Geography.Regions.Asia.Asia*": 0.053922826964153146,
                            "Geography.Regions.Asia.Central Asia": 0.0010540191978565911,
                            "Geography.Regions.Asia.East Asia": 0.00015859255536353935,
                            "Geography.Regions.Asia.North Asia": 0.001639170606177736,
                            "Geography.Regions.Asia.South Asia": 0.00037981554072521193,
                            "Geography.Regions.Asia.Southeast Asia": 0.1295969844969788,
                            "Geography.Regions.Asia.West Asia": 0.0015758566417359654,
                            "Geography.Regions.Europe.Eastern Europe": 0.006411703844818901,
                            "Geography.Regions.Europe.Europe*": 0.04052637386454308,
                            "Geography.Regions.Europe.Northern Europe": 0.009986087621959145,
                            "Geography.Regions.Europe.Southern Europe": 0.009068248925919975,
                            "Geography.Regions.Europe.Western Europe": 0.011069800202305278,
                            "Geography.Regions.Oceania": 0.015890609972399248,
                            "History and Society.Business and economics": 0.0993963928524104,
                            "History and Society.Education": 0.06430872652420767,
                            "History and Society.History": 0.03888750510751568,
                            "History and Society.Military and warfare": 0.0011597465887236648,
                            "History and Society.Politics and government": 0.3817495049698054,
                            "History and Society.Society": 0.06829869812261144,
                            "History and Society.Transportation": 0.0014330186028741118,
                            "STEM.Biology": 0.004779911679802516,
                            "STEM.Chemistry": 0.0005351128777525615,
                            "STEM.Computing": 0.1260141460713239,
                            "STEM.Earth and environment": 0.01341887313175579,
                            "STEM.Engineering": 0.021532699737598353,
                            "STEM.Libraries & Information": 0.000143195569809031,
                            "STEM.Mathematics": 0.028134438670921486,
                            "STEM.Medicine & Health": 0.016469415539396397,
                            "STEM.Physics": 0.015386187697739985,
                            "STEM.STEM*": 0.9754797739642432,
                            "STEM.Space": 0.0026360704668903583,
                            "STEM.Technology": 0.05185008787196212
                        }
                    }
                }
            }
        }
    }
}

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_Vietnamese_Wikipedia_article_topic,
  title={ Vietnamese Wikipedia article topic model card },
  author={ Triedman, Harold and Bazira, Kevin },
  year={ 2023 },
  url={ https://meta.wikimedia.org/wiki/Machine_learning_models/Production/Vietnamese_Wikipedia_article_topic }
}