Machine learning models/Production/Serbian 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?	Serbian 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/srwiki/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*	13381	11913	1468	713	43322
Culture.Biography.Women	3703	2961	742	284	53429
Culture.Food and drink	1377	824	553	164	55875
Culture.Internet culture	2959	2514	445	228	54229
Culture.Linguistics	1601	1150	451	129	55686
Culture.Literature	5115	3833	1282	421	51880
Culture.Media.Books	1560	1238	322	97	55759
Culture.Media.Entertainment	2246	1192	1054	218	54952
Culture.Media.Films	2674	2333	341	106	54636
Culture.Media.Media*	12684	11238	1446	1123	43609
Culture.Media.Music	2694	2253	441	165	54557
Culture.Media.Radio	284	200	84	26	57106
Culture.Media.Software	2267	1929	338	250	54899
Culture.Media.Television	2400	2048	352	103	54913
Culture.Media.Video games	1405	1327	78	37	55974
Culture.Performing arts	1449	807	642	120	55847
Culture.Philosophy and religion	4226	2410	1816	453	52737
Culture.Sports	5082	4504	578	140	52194
Culture.Visual arts.Architecture	1985	1246	739	204	55227
Culture.Visual arts.Comics and Anime	1324	1122	202	72	56020
Culture.Visual arts.Fashion	646	341	305	50	56720
Culture.Visual arts.Visual arts*	4640	2945	1695	387	52389
Geography.Geographical	5060	3705	1355	796	51560
Geography.Regions.Africa.Africa*	3847	2602	1245	291	53278
Geography.Regions.Africa.Central Africa	537	274	263	58	56821
Geography.Regions.Africa.Eastern Africa	449	282	167	44	56923
Geography.Regions.Africa.Northern Africa	1505	1015	490	125	55786
Geography.Regions.Africa.Southern Africa	625	380	245	45	56746
Geography.Regions.Africa.Western Africa	150	102	48	24	57242
Geography.Regions.Americas.Central America	1314	602	712	86	56016
Geography.Regions.Americas.North America	6102	4272	1830	738	50576
Geography.Regions.Americas.South America	1547	1020	527	101	55768
Geography.Regions.Asia.Asia*	10008	7945	2063	777	46631
Geography.Regions.Asia.Central Asia	1120	756	364	70	56226
Geography.Regions.Asia.East Asia	2638	2062	576	103	54675
Geography.Regions.Asia.North Asia	1984	1456	528	274	55158
Geography.Regions.Asia.South Asia	1784	1277	507	64	55568
Geography.Regions.Asia.Southeast Asia	1588	1078	510	102	55726
Geography.Regions.Asia.West Asia	2753	1950	803	221	54442
Geography.Regions.Europe.Eastern Europe	4176	3084	1092	369	52871
Geography.Regions.Europe.Europe*	16664	13521	3143	2059	38693
Geography.Regions.Europe.Northern Europe	3404	2231	1173	244	53768
Geography.Regions.Europe.Southern Europe	6030	4566	1464	668	50718
Geography.Regions.Europe.Western Europe	4302	3277	1025	320	52794
Geography.Regions.Oceania	1836	1260	576	88	55492
History and Society.Business and economics	3143	1856	1287	280	53993
History and Society.Education	1669	857	812	113	55634
History and Society.History	6814	4435	2379	904	49698
History and Society.Military and warfare	5875	4303	1572	638	50903
History and Society.Politics and government	4679	2720	1959	462	52275
History and Society.Society	6974	3425	3549	613	49829
History and Society.Transportation	3236	2923	313	95	54085
STEM.Biology	3787	3111	676	159	53470
STEM.Chemistry	2144	1639	505	342	54930
STEM.Computing	2657	2252	405	255	54504
STEM.Earth and environment	1681	1018	663	155	55580
STEM.Engineering	2820	2183	637	147	54449
STEM.Libraries & Information	516	382	134	26	56874
STEM.Mathematics	573	351	222	53	56790
STEM.Medicine & Health	2450	1738	712	258	54708
STEM.Physics	1431	1039	392	160	55825
STEM.STEM*	18323	16602	1721	950	38143
STEM.Space	2151	2029	122	25	55240
STEM.Technology	4652	3536	1116	522	52242

Test data sample rates:

Test data sample rates

Label	Sample	Population
Culture.Biography.Biography*	0.233	0.123
Culture.Biography.Women	0.064	0.015
Culture.Food and drink	0.024	0.002
Culture.Internet culture	0.052	0.003
Culture.Linguistics	0.028	0.007
Culture.Literature	0.089	0.015
Culture.Media.Books	0.027	0.004
Culture.Media.Entertainment	0.039	0.004
Culture.Media.Films	0.047	0.011
Culture.Media.Media*	0.221	0.058
Culture.Media.Music	0.047	0.024
Culture.Media.Radio	0.005	0.002
Culture.Media.Software	0.039	0.001
Culture.Media.Television	0.042	0.009
Culture.Media.Video games	0.024	0.003
Culture.Performing arts	0.025	0.003
Culture.Philosophy and religion	0.074	0.011
Culture.Sports	0.089	0.071
Culture.Visual arts.Architecture	0.035	0.011
Culture.Visual arts.Comics and Anime	0.023	0.002
Culture.Visual arts.Fashion	0.011	0.001
Culture.Visual arts.Visual arts*	0.081	0.018
Geography.Geographical	0.088	0.024
Geography.Regions.Africa.Africa*	0.067	0.008
Geography.Regions.Africa.Central Africa	0.009	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	0.023	0.003
Geography.Regions.Americas.North America	0.106	0.064
Geography.Regions.Americas.South America	0.027	0.006
Geography.Regions.Asia.Asia*	0.174	0.045
Geography.Regions.Asia.Central Asia	0.02	0.001
Geography.Regions.Asia.East Asia	0.046	0.011
Geography.Regions.Asia.North Asia	0.035	0.001
Geography.Regions.Asia.South Asia	0.031	0.015
Geography.Regions.Asia.Southeast Asia	0.028	0.006
Geography.Regions.Asia.West Asia	0.048	0.011
Geography.Regions.Europe.Eastern Europe	0.073	0.013
Geography.Regions.Europe.Europe*	0.29	0.076
Geography.Regions.Europe.Northern Europe	0.059	0.031
Geography.Regions.Europe.Southern Europe	0.105	0.013
Geography.Regions.Europe.Western Europe	0.075	0.019
Geography.Regions.Oceania	0.032	0.015
History and Society.Business and economics	0.055	0.01
History and Society.Education	0.029	0.007
History and Society.History	0.119	0.011
History and Society.Military and warfare	0.102	0.014
History and Society.Politics and government	0.081	0.028
History and Society.Society	0.121	0.013
History and Society.Transportation	0.056	0.015
STEM.Biology	0.066	0.034
STEM.Chemistry	0.037	0.002
STEM.Computing	0.046	0.003
STEM.Earth and environment	0.029	0.005
STEM.Engineering	0.049	0.005
STEM.Libraries & Information	0.009	0.001
STEM.Mathematics	0.01	0
STEM.Medicine & Health	0.043	0.006
STEM.Physics	0.025	0.001
STEM.STEM*	0.319	0.069
STEM.Space	0.037	0.006
STEM.Technology	0.081	0.005

Test data performance:

Test data performance

Label	Match rate	Filter rate	Recall	Precision	f1	Accuracy	ROC AUC	PR AUC
Culture.Biography.Biography*	0.124	0.876	0.89	0.885	0.888	0.972	0.981	0.94
Culture.Biography.Women	0.017	0.983	0.8	0.691	0.741	0.992	0.984	0.762
Culture.Food and drink	0.004	0.996	0.598	0.335	0.43	0.996	0.973	0.419
Culture.Internet culture	0.007	0.993	0.85	0.416	0.559	0.995	0.986	0.673
Culture.Linguistics	0.008	0.992	0.718	0.696	0.707	0.996	0.976	0.672
Culture.Literature	0.02	0.98	0.749	0.594	0.663	0.988	0.979	0.723
Culture.Media.Books	0.005	0.995	0.794	0.649	0.714	0.997	0.985	0.718
Culture.Media.Entertainment	0.006	0.994	0.531	0.326	0.404	0.994	0.972	0.331
Culture.Media.Films	0.011	0.989	0.872	0.827	0.849	0.997	0.986	0.887
Culture.Media.Media*	0.075	0.925	0.886	0.687	0.774	0.97	0.981	0.872
Culture.Media.Music	0.023	0.977	0.836	0.872	0.854	0.993	0.984	0.888
Culture.Media.Radio	0.002	0.998	0.704	0.77	0.735	0.999	0.945	0.563
Culture.Media.Software	0.006	0.994	0.851	0.2	0.324	0.995	0.987	0.382
Culture.Media.Television	0.009	0.991	0.853	0.802	0.827	0.997	0.985	0.851
Culture.Media.Video games	0.003	0.997	0.944	0.789	0.86	0.999	0.988	0.914
Culture.Performing arts	0.004	0.996	0.557	0.429	0.485	0.997	0.97	0.38
Culture.Philosophy and religion	0.014	0.986	0.57	0.419	0.483	0.987	0.955	0.464
Culture.Sports	0.066	0.934	0.886	0.962	0.923	0.989	0.981	0.953
Culture.Visual arts.Architecture	0.01	0.99	0.628	0.646	0.636	0.992	0.978	0.626
Culture.Visual arts.Comics and Anime	0.003	0.997	0.847	0.592	0.697	0.998	0.988	0.767
Culture.Visual arts.Fashion	0.001	0.999	0.528	0.327	0.404	0.999	0.966	0.243
Culture.Visual arts.Visual arts*	0.019	0.981	0.635	0.617	0.626	0.986	0.967	0.651
Geography.Geographical	0.032	0.968	0.732	0.538	0.62	0.979	0.973	0.637
Geography.Regions.Africa.Africa*	0.011	0.989	0.676	0.495	0.571	0.992	0.973	0.564
Geography.Regions.Africa.Central Africa	0.001	0.999	0.51	0.24	0.327	0.999	0.972	0.171
Geography.Regions.Africa.Eastern Africa	0.001	0.999	0.628	0.27	0.378	0.999	0.971	0.167
Geography.Regions.Africa.Northern Africa	0.003	0.997	0.674	0.27	0.386	0.997	0.976	0.337
Geography.Regions.Africa.Southern Africa	0.002	0.998	0.608	0.474	0.533	0.999	0.969	0.42
Geography.Regions.Africa.Western Africa	0.001	0.999	0.68	0.526	0.593	0.999	0.908	0.414
Geography.Regions.Americas.Central America	0.003	0.997	0.458	0.497	0.477	0.997	0.963	0.385
Geography.Regions.Americas.North America	0.058	0.942	0.7	0.77	0.733	0.967	0.97	0.803
Geography.Regions.Americas.South America	0.006	0.994	0.659	0.698	0.678	0.996	0.977	0.671
Geography.Regions.Asia.Asia*	0.052	0.948	0.794	0.698	0.743	0.975	0.974	0.827
Geography.Regions.Asia.Central Asia	0.002	0.998	0.675	0.32	0.434	0.998	0.979	0.333
Geography.Regions.Asia.East Asia	0.011	0.989	0.782	0.828	0.804	0.996	0.984	0.853
Geography.Regions.Asia.North Asia	0.006	0.994	0.734	0.121	0.207	0.995	0.985	0.174
Geography.Regions.Asia.South Asia	0.012	0.988	0.716	0.906	0.8	0.995	0.979	0.84
Geography.Regions.Asia.Southeast Asia	0.006	0.994	0.679	0.692	0.685	0.996	0.975	0.659
Geography.Regions.Asia.West Asia	0.012	0.988	0.708	0.659	0.683	0.993	0.974	0.679
Geography.Regions.Europe.Eastern Europe	0.016	0.984	0.739	0.581	0.65	0.99	0.979	0.697
Geography.Regions.Europe.Europe*	0.108	0.892	0.811	0.57	0.669	0.939	0.959	0.771
Geography.Regions.Europe.Northern Europe	0.024	0.976	0.655	0.821	0.729	0.985	0.973	0.787
Geography.Regions.Europe.Southern Europe	0.023	0.977	0.757	0.435	0.552	0.984	0.974	0.621
Geography.Regions.Europe.Western Europe	0.021	0.979	0.762	0.712	0.736	0.99	0.979	0.804
Geography.Regions.Oceania	0.012	0.988	0.686	0.869	0.767	0.994	0.975	0.814
History and Society.Business and economics	0.011	0.989	0.591	0.538	0.563	0.991	0.961	0.517
History and Society.Education	0.006	0.994	0.513	0.652	0.575	0.994	0.963	0.551
History and Society.History	0.025	0.975	0.651	0.285	0.397	0.979	0.96	0.439
History and Society.Military and warfare	0.023	0.977	0.732	0.458	0.563	0.984	0.972	0.629
History and Society.Politics and government	0.025	0.975	0.581	0.658	0.617	0.98	0.957	0.657
History and Society.Society	0.018	0.982	0.491	0.34	0.402	0.982	0.929	0.365
History and Society.Transportation	0.015	0.985	0.903	0.887	0.895	0.997	0.987	0.935
STEM.Biology	0.03	0.97	0.821	0.906	0.862	0.991	0.98	0.9
STEM.Chemistry	0.007	0.993	0.764	0.162	0.267	0.993	0.987	0.244
STEM.Computing	0.007	0.993	0.848	0.329	0.474	0.995	0.988	0.577
STEM.Earth and environment	0.006	0.994	0.606	0.498	0.547	0.995	0.971	0.526
STEM.Engineering	0.007	0.993	0.774	0.602	0.677	0.996	0.981	0.723
STEM.Libraries & Information	0.001	0.999	0.74	0.502	0.598	0.999	0.967	0.466
STEM.Mathematics	0.001	0.999	0.613	0.215	0.318	0.999	0.967	0.148
STEM.Medicine & Health	0.009	0.991	0.709	0.493	0.582	0.993	0.98	0.657
STEM.Physics	0.003	0.997	0.726	0.178	0.285	0.997	0.983	0.293
STEM.STEM*	0.085	0.915	0.906	0.735	0.811	0.971	0.98	0.914
STEM.Space	0.006	0.994	0.943	0.927	0.935	0.999	0.99	0.957
STEM.Technology	0.014	0.986	0.76	0.284	0.413	0.989	0.978	0.467

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/srwiki/1234/articletopic

Output:

Example output

{
    "srwiki": {
        "models": {
            "articletopic": {
                "version": "1.4.0"
            }
        },
        "scores": {
            "1234": {
                "articletopic": {
                    "score": {
                        "prediction": [
                            "Geography.Regions.Europe.Europe*"
                        ],
                        "probability": {
                            "Culture.Biography.Biography*": 0.11040104750780567,
                            "Culture.Biography.Women": 0.13470931374358366,
                            "Culture.Food and drink": 0.001061695465685582,
                            "Culture.Internet culture": 0.0011464255449539539,
                            "Culture.Linguistics": 0.0015135201814895013,
                            "Culture.Literature": 0.2372278579844666,
                            "Culture.Media.Books": 0.03278657586800802,
                            "Culture.Media.Entertainment": 0.013682928395192407,
                            "Culture.Media.Films": 0.0019281923818669927,
                            "Culture.Media.Media*": 0.21500396074659422,
                            "Culture.Media.Music": 0.006457968301838956,
                            "Culture.Media.Radio": 5.324926349730714e-05,
                            "Culture.Media.Software": 0.0016168087230442878,
                            "Culture.Media.Television": 0.0008242222680444264,
                            "Culture.Media.Video games": 0.00015369555726823047,
                            "Culture.Performing arts": 0.019747694393684182,
                            "Culture.Philosophy and religion": 0.022521115478092234,
                            "Culture.Sports": 0.0006649569081514491,
                            "Culture.Visual arts.Architecture": 0.0014359201662917907,
                            "Culture.Visual arts.Comics and Anime": 0.0008204187925402861,
                            "Culture.Visual arts.Fashion": 0.003749338967508995,
                            "Culture.Visual arts.Visual arts*": 0.01239033143459835,
                            "Geography.Geographical": 0.0020590554403184342,
                            "Geography.Regions.Africa.Africa*": 0.009497069772931837,
                            "Geography.Regions.Africa.Central Africa": 0.00019369006146811776,
                            "Geography.Regions.Africa.Eastern Africa": 0.0015356466692226847,
                            "Geography.Regions.Africa.Northern Africa": 0.005336316892577839,
                            "Geography.Regions.Africa.Southern Africa": 0.00033412592938185316,
                            "Geography.Regions.Africa.Western Africa": 8.839117892978597e-06,
                            "Geography.Regions.Americas.Central America": 0.005021089209446801,
                            "Geography.Regions.Americas.North America": 0.005561597081477266,
                            "Geography.Regions.Americas.South America": 0.011508840556108442,
                            "Geography.Regions.Asia.Asia*": 0.04194057214043255,
                            "Geography.Regions.Asia.Central Asia": 0.004133622146411763,
                            "Geography.Regions.Asia.East Asia": 0.0010214193696603039,
                            "Geography.Regions.Asia.North Asia": 0.006348550312943161,
                            "Geography.Regions.Asia.South Asia": 0.0021167821977180414,
                            "Geography.Regions.Asia.Southeast Asia": 0.002635200732815336,
                            "Geography.Regions.Asia.West Asia": 0.005865910117755206,
                            "Geography.Regions.Europe.Eastern Europe": 0.24693488970957647,
                            "Geography.Regions.Europe.Europe*": 0.5617995769783409,
                            "Geography.Regions.Europe.Northern Europe": 0.007852167426943286,
                            "Geography.Regions.Europe.Southern Europe": 0.14698569063311887,
                            "Geography.Regions.Europe.Western Europe": 0.030190015010303623,
                            "Geography.Regions.Oceania": 0.006497928041576333,
                            "History and Society.Business and economics": 0.006484597136562253,
                            "History and Society.Education": 0.005663187639018815,
                            "History and Society.History": 0.4909693515351464,
                            "History and Society.Military and warfare": 0.020405610349156465,
                            "History and Society.Politics and government": 0.030881580068143677,
                            "History and Society.Society": 0.1450441646414019,
                            "History and Society.Transportation": 0.0004588823814014062,
                            "STEM.Biology": 0.002932193824382193,
                            "STEM.Chemistry": 0.00022682623322946885,
                            "STEM.Computing": 0.0009886969673890645,
                            "STEM.Earth and environment": 0.0005888236822300564,
                            "STEM.Engineering": 0.0009121741948055364,
                            "STEM.Libraries & Information": 0.00021451702119693527,
                            "STEM.Mathematics": 0.0006612514517849881,
                            "STEM.Medicine & Health": 0.00045552016112214335,
                            "STEM.Physics": 0.0003670794434625032,
                            "STEM.STEM*": 0.06676165100619627,
                            "STEM.Space": 0.00010645677663643897,
                            "STEM.Technology": 0.0016211512153451234
                        }
                    }
                }
            }
        }
    }
}

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