Machine learning models/Production/Armenian Wikipedia article topic

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?	Armenian Wikipedia
This model uses article text to predict the likelihood that the article belongs to a set of topics.

Motivation

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

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/hywiki/8658862/articletopic

Ethical considerations, caveats, and recommendations

• 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

Performance

Test data confusion matrix:

Test data confusion matrix
Label n True positive False positive False negative True Negative Culture.Biography.Biography* 15686 14429 1257 647 39218 Culture.Biography.Women 4518 3350 1168 476 50557 Culture.Food and drink 1662 1335 327 105 53784 Culture.Internet culture 2507 2098 409 144 52900 Culture.Linguistics 1693 1244 449 66 53792 Culture.Literature 5298 4042 1256 486 49767 Culture.Media.Books 1758 1483 275 100 53693 Culture.Media.Entertainment 2153 1049 1104 175 53223 Culture.Media.Films 3018 2658 360 122 52411 Culture.Media.Media* 13233 11667 1566 1138 41180 Culture.Media.Music 3428 2921 507 239 51884 Culture.Media.Radio 233 170 63 28 55290 Culture.Media.Software 2201 2065 136 162 53188 Culture.Media.Television 2078 1685 393 102 53371 Culture.Media.Video games 766 728 38 16 54769 Culture.Performing arts 1734 1203 531 121 53696 Culture.Philosophy and religion 3901 2179 1722 366 51284 Culture.Sports 3288 2775 513 95 52168 Culture.Visual arts.Architecture 2452 1945 507 239 52860 Culture.Visual arts.Comics and Anime 1071 909 162 44 54436 Culture.Visual arts.Fashion 820 610 210 45 54686 Culture.Visual arts.Visual arts* 5439 4133 1306 482 49630 Geography.Geographical 4862 3583 1279 608 50081 Geography.Regions.Africa.Africa* 3298 2034 1264 186 52067 Geography.Regions.Africa.Central Africa 401 261 140 32 55118 Geography.Regions.Africa.Eastern Africa 256 188 68 25 55270 Geography.Regions.Africa.Northern Africa 1335 896 439 93 54123 Geography.Regions.Africa.Southern Africa 605 466 139 14 54932 Geography.Regions.Africa.Western Africa 140 99 41 39 55372 Geography.Regions.Americas.Central America 1256 585 671 51 54244 Geography.Regions.Americas.North America 5910 4274 1636 778 48863 Geography.Regions.Americas.South America 1669 1311 358 62 53820 Geography.Regions.Asia.Asia* 12149 9899 2250 1078 42324 Geography.Regions.Asia.Central Asia 1088 718 370 68 54395 Geography.Regions.Asia.East Asia 2652 2201 451 100 52799 Geography.Regions.Asia.North Asia 2562 1910 652 333 52656 Geography.Regions.Asia.South Asia 1924 1380 544 65 53562 Geography.Regions.Asia.Southeast Asia 1456 774 682 55 54040 Geography.Regions.Asia.West Asia 4499 3564 935 369 50683 Geography.Regions.Europe.Eastern Europe 4478 3397 1081 396 50677 Geography.Regions.Europe.Europe* 16951 13906 3045 1930 36670 Geography.Regions.Europe.Northern Europe 4245 3158 1087 315 50991 Geography.Regions.Europe.Southern Europe 4409 3414 995 289 50853 Geography.Regions.Europe.Western Europe 4936 3955 981 396 50219 Geography.Regions.Oceania 1674 1025 649 72 53805 History and Society.Business and economics 3475 2362 1113 297 51779 History and Society.Education 1893 1199 694 125 53533 History and Society.History 5858 3535 2323 743 48950 History and Society.Military and warfare 5200 3672 1528 626 49725 History and Society.Politics and government 4691 2637 2054 481 50379 History and Society.Society 7986 4395 3591 744 46821 History and Society.Transportation 2514 2168 346 85 52952 STEM.Biology 3086 2423 663 156 52309 STEM.Chemistry 1651 1400 251 130 53770 STEM.Computing 2282 1963 319 168 53101 STEM.Earth and environment 1861 1308 553 120 53570 STEM.Engineering 2812 2190 622 200 52539 STEM.Libraries & Information 503 391 112 37 55011 STEM.Mathematics 592 492 100 30 54929 STEM.Medicine & Health 2084 1592 492 140 53327 STEM.Physics 1667 1315 352 142 53742 STEM.STEM* 16786 15011 1775 848 37917 STEM.Space 2077 1950 127 39 53435 STEM.Technology 4483 3448 1035 498 50570

Test data sample rates:

Test data sample rates
Label Sample Population Culture.Biography.Biography* 0.282 0.123 Culture.Biography.Women 0.081 0.015 Culture.Food and drink 0.03 0.002 Culture.Internet culture 0.045 0.003 Culture.Linguistics 0.03 0.007 Culture.Literature 0.095 0.015 Culture.Media.Books 0.032 0.004 Culture.Media.Entertainment 0.039 0.004 Culture.Media.Films 0.054 0.011 Culture.Media.Media* 0.238 0.058 Culture.Media.Music 0.062 0.024 Culture.Media.Radio 0.004 0.002 Culture.Media.Software 0.04 0.001 Culture.Media.Television 0.037 0.009 Culture.Media.Video games 0.014 0.003 Culture.Performing arts 0.031 0.003 Culture.Philosophy and religion 0.07 0.011 Culture.Sports 0.059 0.071 Culture.Visual arts.Architecture 0.044 0.011 Culture.Visual arts.Comics and Anime 0.019 0.002 Culture.Visual arts.Fashion 0.015 0.001 Culture.Visual arts.Visual arts* 0.098 0.018 Geography.Geographical 0.088 0.024 Geography.Regions.Africa.Africa* 0.059 0.008 Geography.Regions.Africa.Central Africa 0.007 0.001 Geography.Regions.Africa.Eastern Africa 0.005 0 Geography.Regions.Africa.Northern Africa 0.024 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 0.03 0.006 Geography.Regions.Asia.Asia* 0.219 0.045 Geography.Regions.Asia.Central Asia 0.02 0.001 Geography.Regions.Asia.East Asia 0.048 0.011 Geography.Regions.Asia.North Asia 0.046 0.001 Geography.Regions.Asia.South Asia 0.035 0.015 Geography.Regions.Asia.Southeast Asia 0.026 0.006 Geography.Regions.Asia.West Asia 0.081 0.011 Geography.Regions.Europe.Eastern Europe 0.081 0.013 Geography.Regions.Europe.Europe* 0.305 0.076 Geography.Regions.Europe.Northern Europe 0.076 0.031 Geography.Regions.Europe.Southern Europe 0.079 0.013 Geography.Regions.Europe.Western Europe 0.089 0.019 Geography.Regions.Oceania 0.03 0.015 History and Society.Business and economics 0.063 0.01 History and Society.Education 0.034 0.007 History and Society.History 0.105 0.011 History and Society.Military and warfare 0.094 0.014 History and Society.Politics and government 0.084 0.028 History and Society.Society 0.144 0.013 History and Society.Transportation 0.045 0.015 STEM.Biology 0.056 0.034 STEM.Chemistry 0.03 0.002 STEM.Computing 0.041 0.003 STEM.Earth and environment 0.034 0.005 STEM.Engineering 0.051 0.005 STEM.Libraries & Information 0.009 0.001 STEM.Mathematics 0.011 0 STEM.Medicine & Health 0.038 0.006 STEM.Physics 0.03 0.001 STEM.STEM* 0.302 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* 0.127 0.873 0.92 0.888 0.904 0.976 0.983 0.956 Culture.Biography.Women 0.02 0.98 0.741 0.54 0.625 0.987 0.981 0.627 Culture.Food and drink 0.004 0.996 0.803 0.504 0.62 0.998 0.984 0.697 Culture.Internet culture 0.006 0.994 0.837 0.52 0.641 0.997 0.985 0.714 Culture.Linguistics 0.007 0.993 0.735 0.816 0.773 0.997 0.978 0.781 Culture.Literature 0.021 0.979 0.763 0.554 0.642 0.987 0.976 0.696 Culture.Media.Books 0.005 0.995 0.844 0.647 0.732 0.998 0.987 0.762 Culture.Media.Entertainment 0.005 0.995 0.487 0.348 0.406 0.995 0.969 0.332 Culture.Media.Films 0.012 0.988 0.881 0.801 0.839 0.996 0.987 0.897 Culture.Media.Media* 0.077 0.923 0.882 0.671 0.762 0.968 0.98 0.854 Culture.Media.Music 0.025 0.975 0.852 0.82 0.836 0.992 0.986 0.894 Culture.Media.Radio 0.002 0.998 0.73 0.757 0.743 0.999 0.916 0.533 Culture.Media.Software 0.004 0.996 0.938 0.291 0.444 0.997 0.988 0.496 Culture.Media.Television 0.009 0.991 0.811 0.791 0.801 0.996 0.983 0.807 Culture.Media.Video games 0.003 0.997 0.95 0.895 0.922 1 0.985 0.945 Culture.Performing arts 0.004 0.996 0.694 0.472 0.562 0.997 0.979 0.52 Culture.Philosophy and religion 0.013 0.987 0.559 0.459 0.504 0.988 0.955 0.506 Culture.Sports 0.062 0.938 0.844 0.973 0.904 0.987 0.979 0.948 Culture.Visual arts.Architecture 0.013 0.987 0.793 0.653 0.716 0.993 0.986 0.729 Culture.Visual arts.Comics and Anime 0.003 0.997 0.849 0.698 0.766 0.999 0.986 0.802 Culture.Visual arts.Fashion 0.001 0.999 0.744 0.423 0.539 0.999 0.982 0.439 Culture.Visual arts.Visual arts* 0.023 0.977 0.76 0.595 0.668 0.986 0.977 0.673 Geography.Geographical 0.029 0.971 0.737 0.597 0.66 0.982 0.975 0.704 Geography.Regions.Africa.Africa* 0.008 0.992 0.617 0.577 0.596 0.993 0.969 0.552 Geography.Regions.Africa.Central Africa 0.001 0.999 0.651 0.415 0.507 0.999 0.976 0.331 Geography.Regions.Africa.Eastern Africa 0.001 0.999 0.734 0.425 0.538 0.999 0.944 0.311 Geography.Regions.Africa.Northern Africa 0.003 0.997 0.671 0.325 0.438 0.998 0.979 0.359 Geography.Regions.Africa.Southern Africa 0.001 0.999 0.77 0.781 0.775 0.999 0.975 0.618 Geography.Regions.Africa.Western Africa 0.001 0.999 0.707 0.407 0.517 0.999 0.882 0.24 Geography.Regions.Americas.Central America 0.002 0.998 0.466 0.621 0.532 0.997 0.956 0.414 Geography.Regions.Americas.North America 0.061 0.939 0.723 0.76 0.741 0.968 0.972 0.801 Geography.Regions.Americas.South America 0.006 0.994 0.786 0.812 0.799 0.998 0.981 0.841 Geography.Regions.Asia.Asia* 0.061 0.939 0.815 0.61 0.698 0.968 0.971 0.76 Geography.Regions.Asia.Central Asia 0.002 0.998 0.66 0.314 0.426 0.998 0.976 0.358 Geography.Regions.Asia.East Asia 0.011 0.989 0.83 0.835 0.833 0.996 0.985 0.856 Geography.Regions.Asia.North Asia 0.007 0.993 0.746 0.099 0.175 0.993 0.984 0.18 Geography.Regions.Asia.South Asia 0.012 0.988 0.717 0.901 0.799 0.995 0.977 0.84 Geography.Regions.Asia.Southeast Asia 0.004 0.996 0.532 0.76 0.625 0.996 0.962 0.576 Geography.Regions.Asia.West Asia 0.016 0.984 0.792 0.547 0.647 0.991 0.982 0.676 Geography.Regions.Europe.Eastern Europe 0.017 0.983 0.759 0.56 0.644 0.989 0.979 0.677 Geography.Regions.Europe.Europe* 0.109 0.891 0.82 0.575 0.676 0.94 0.961 0.768 Geography.Regions.Europe.Northern Europe 0.029 0.971 0.744 0.793 0.767 0.986 0.978 0.83 Geography.Regions.Europe.Southern Europe 0.016 0.984 0.774 0.644 0.703 0.991 0.979 0.741 Geography.Regions.Europe.Western Europe 0.023 0.977 0.801 0.667 0.728 0.989 0.981 0.798 Geography.Regions.Oceania 0.011 0.989 0.612 0.876 0.721 0.993 0.97 0.743 History and Society.Business and economics 0.013 0.987 0.68 0.548 0.607 0.991 0.971 0.624 History and Society.Education 0.007 0.993 0.633 0.668 0.65 0.995 0.973 0.603 History and Society.History 0.021 0.979 0.603 0.307 0.407 0.981 0.953 0.393 History and Society.Military and warfare 0.022 0.978 0.706 0.448 0.548 0.984 0.972 0.577 History and Society.Politics and government 0.025 0.975 0.562 0.633 0.595 0.978 0.957 0.63 History and Society.Society 0.022 0.978 0.55 0.31 0.397 0.979 0.935 0.386 History and Society.Transportation 0.015 0.985 0.862 0.892 0.877 0.996 0.985 0.903 STEM.Biology 0.029 0.971 0.785 0.902 0.839 0.99 0.984 0.903 STEM.Chemistry 0.004 0.996 0.848 0.354 0.5 0.997 0.989 0.571 STEM.Computing 0.005 0.995 0.86 0.424 0.568 0.996 0.987 0.579 STEM.Earth and environment 0.005 0.995 0.703 0.589 0.641 0.996 0.974 0.616 STEM.Engineering 0.008 0.992 0.779 0.519 0.623 0.995 0.982 0.659 STEM.Libraries & Information 0.001 0.999 0.777 0.418 0.544 0.999 0.964 0.422 STEM.Mathematics 0.001 0.999 0.831 0.388 0.529 0.999 0.978 0.456 STEM.Medicine & Health 0.007 0.993 0.764 0.653 0.704 0.996 0.981 0.686 STEM.Physics 0.003 0.997 0.789 0.203 0.323 0.997 0.986 0.278 STEM.STEM* 0.082 0.918 0.894 0.752 0.817 0.972 0.978 0.901 STEM.Space 0.006 0.994 0.939 0.886 0.912 0.999 0.993 0.946 STEM.Technology 0.014 0.986 0.769 0.289 0.42 0.989 0.978 0.514

The training dataset for this model is available here.

Implementation

Model architecture

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

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/hywiki/8658862/articletopic

Output:

Example output
{ "hywiki": { "models": { "articletopic": { "version": "1.4.0" } }, "scores": { "8658862": { "articletopic": { "score": { "prediction": [ "Geography.Regions.Asia.Asia*", "Geography.Regions.Asia.South Asia" ], "probability": { "Culture.Biography.Biography*": 0.02422244388067302, "Culture.Biography.Women": 0.004590189485908635, "Culture.Food and drink": 0.000593925273532745, "Culture.Internet culture": 0.0012627822764779287, "Culture.Linguistics": 0.003555844037516116, "Culture.Literature": 0.005544604789740323, "Culture.Media.Books": 0.001158495969631809, "Culture.Media.Entertainment": 0.0018323597994658433, "Culture.Media.Films": 0.00033560605162936974, "Culture.Media.Media*": 0.0045343813847354905, "Culture.Media.Music": 0.0004843346548800057, "Culture.Media.Radio": 1.392574877538206e-05, "Culture.Media.Software": 0.00025844073978464595, "Culture.Media.Television": 0.00034419434308919776, "Culture.Media.Video games": 4.280533183432128e-05, "Culture.Performing arts": 0.00063179156072444, "Culture.Philosophy and religion": 0.3711155137903629, "Culture.Sports": 0.0036244519038555697, "Culture.Visual arts.Architecture": 0.0028136699436777427, "Culture.Visual arts.Comics and Anime": 0.0001390074106899022, "Culture.Visual arts.Fashion": 0.0007178288823863084, "Culture.Visual arts.Visual arts*": 0.005269038325102219, "Geography.Geographical": 0.2524351124002908, "Geography.Regions.Africa.Africa*": 0.012126621454447192, "Geography.Regions.Africa.Central Africa": 5.914727944463523e-05, "Geography.Regions.Africa.Eastern Africa": 0.0009634788615136871, "Geography.Regions.Africa.Northern Africa": 0.0014164304776163943, "Geography.Regions.Africa.Southern Africa": 0.0002584714601394708, "Geography.Regions.Africa.Western Africa": 9.301139644499533e-06, "Geography.Regions.Americas.Central America": 0.004175898142649278, "Geography.Regions.Americas.North America": 0.009485683925882019, "Geography.Regions.Americas.South America": 0.000401632042878274, "Geography.Regions.Asia.Asia*": 0.9910897147526467, "Geography.Regions.Asia.Central Asia": 0.004504171246660892, "Geography.Regions.Asia.East Asia": 0.01792040515979525, "Geography.Regions.Asia.North Asia": 0.0011675076943681829, "Geography.Regions.Asia.South Asia": 0.998360899663115, "Geography.Regions.Asia.Southeast Asia": 0.09796124031125475, "Geography.Regions.Asia.West Asia": 0.022082349127207978, "Geography.Regions.Europe.Eastern Europe": 0.007670121398609532, "Geography.Regions.Europe.Europe*": 0.017986477795028887, "Geography.Regions.Europe.Northern Europe": 0.006012507157508805, "Geography.Regions.Europe.Southern Europe": 0.00604176949302703, "Geography.Regions.Europe.Western Europe": 0.002840008039240512, "Geography.Regions.Oceania": 0.005502290390648899, "History and Society.Business and economics": 0.028731862343375242, "History and Society.Education": 0.008949469019074941, "History and Society.History": 0.1739217023221256, "History and Society.Military and warfare": 0.03266142222137065, "History and Society.Politics and government": 0.1491903434201552, "History and Society.Society": 0.07254632815381397, "History and Society.Transportation": 0.0003174916188457565, "STEM.Biology": 0.004020816180798944, "STEM.Chemistry": 0.005676249499468716, "STEM.Computing": 0.0017880809490195585, "STEM.Earth and environment": 0.005972258034398003, "STEM.Engineering": 0.003907983077647486, "STEM.Libraries & Information": 0.0005256470127341649, "STEM.Mathematics": 0.00015714078387499814, "STEM.Medicine & Health": 0.005778276394043048, "STEM.Physics": 0.0004302543273463213, "STEM.STEM*": 0.09532948612026247, "STEM.Space": 0.0001287338555615804, "STEM.Technology": 0.00731848551345249 } } } } } } }

Data

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

If available, the training dataset can be found here. 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

• Code: MIT license
• Model: MIT license

Citation

Cite this model card as:

@misc{
  Triedman_Bazira_2023_Armenian_Wikipedia_article_topic,
  title={ Armenian Wikipedia article topic model card },
  author={ Triedman, Harold and Bazira, Kevin },
  year={ 2023 },
  url={ https://meta.wikimedia.org/wiki/Machine_learning_models/Production/Armenian_Wikipedia_article_topic }
}