We want to measure the impact of ORES rollout over time (and impact of anti-vandalism bots) in Wikidata. In order to do so, we can run mwreverts tool on dump of wikidata. It'll be interesting
Description
Status | Subtype | Assigned | Task | ||
---|---|---|---|---|---|
Resolved | Groceryheist | T200898 Analyze the effects of ORES deployments on counter-vandalism behavior | |||
Resolved | Ladsgroup | T189962 Run analysis of revert time and number changes over time for wikidata |
Event Timeline
Analysing the dump has been finished and all of the reverted/reverting edits (metadata only) is a 2.7GB file. I need to download it from stat1005 and run some scripts on top of that to make some histograms and data.
This is result of the analysis (note that I omit any revert that took more than 48 hours in average):
Month | Number of reverts | Average revert time (seconds) | Average revert time (hours) |
2013-02 | 6821 | 7916.928602844161 | 2.199146834123378 |
2013-03 | 17917 | 10196.750739521081 | 2.8324307609780783 |
2013-04 | 34763 | 28276.717889710388 | 7.854643858252885 |
2013-05 | 32516 | 39669.284905892346 | 11.019245807192318 |
2013-06 | 24598 | 28412.00073176681 | 7.892222425490781 |
2013-07 | 7555 | 25306.385837193895 | 7.0295516214427485 |
2013-08 | 8052 | 22222.630029806296 | 6.172952786057304 |
2013-09 | 7114 | 17918.620185549586 | 4.977394495985996 |
2013-10 | 9260 | 41637.55712742978 | 11.565988090952718 |
2013-11 | 10504 | 24780.01675552181 | 6.883337987644947 |
2013-12 | 15180 | 58733.141172595526 | 16.31476143683209 |
2014-01 | 14679 | 49131.30029293547 | 13.647583414704297 |
2014-02 | 17485 | 21576.300085787825 | 5.993416690496618 |
2014-03 | 12635 | 20303.894182825494 | 5.639970606340415 |
2014-04 | 12522 | 25891.221210669202 | 7.192005891852556 |
2014-05 | 15133 | 37105.93543910653 | 10.307204288640703 |
2014-06 | 19371 | 42999.95833978641 | 11.944432872162892 |
2014-07 | 34054 | 61557.150525635836 | 17.09920847934329 |
2014-08 | 15098 | 41466.03225592792 | 11.518342293313312 |
2014-09 | 11549 | 27786.04164862755 | 7.718344902396542 |
2014-10 | 13090 | 36266.25974025998 | 10.073961038961105 |
2014-11 | 34496 | 70138.88665352523 | 19.483024070423674 |
2014-12 | 16044 | 27151.371291448515 | 7.542047580957921 |
2015-01 | 23252 | 36368.31291931882 | 10.102309144255228 |
2015-02 | 21412 | 25898.333971604807 | 7.193981658779113 |
2015-03 | 27341 | 47517.56753593505 | 13.199324315537513 |
2015-04 | 30730 | 63382.18747152633 | 17.606163186535092 |
2015-05 | 14039 | 43292.318398746276 | 12.025643999651743 |
2015-06 | 14073 | 29394.263554323876 | 8.16507320953441 |
2015-07 | 18497 | 42179.56392928587 | 11.716545535912742 |
2015-08 | 17770 | 42958.667979741156 | 11.932963327705878 |
2015-09 | 18581 | 27615.422636026044 | 7.670950732229457 |
2015-10 | 26102 | 35043.90464332238 | 9.734417956478438 |
2015-11 | 45213 | 54039.81697741788 | 15.011060271504967 |
2015-12 | 28413 | 42409.553795797714 | 11.78043160994381 |
2016-01 | 44766 | 60458.55738730213 | 16.794043718695036 |
2016-02 | 23914 | 26297.45002927153 | 7.304847230353203 |
2016-03 | 27773 | 24362.23450833534 | 6.767287363426483 |
2016-04 | 30416 | 36819.45900184132 | 10.227627500511478 |
2016-05 | 21610 | 25219.591022674755 | 7.005441950742988 |
2016-06 | 23020 | 27558.87528236315 | 7.655243133989765 |
2016-07 | 31846 | 29005.43437166382 | 8.05706510323995 |
2016-08 | 18751 | 23268.41123140103 | 6.463447564278064 |
2016-09 | 23275 | 24590.70552094509 | 6.8307515335958575 |
2016-10 | 31119 | 28939.623316944635 | 8.038784254706844 |
2016-11 | 25024 | 24583.590153452697 | 6.828775042625749 |
2016-12 | 26135 | 38474.23145207599 | 10.687286514465553 |
2017-01 | 60342 | 78197.64391302878 | 21.721567753619105 |
2017-02 | 35700 | 29089.152072829147 | 8.08032002023032 |
2017-03 | 48812 | 31783.109829550092 | 8.82864161931947 |
2017-04 | 27049 | 29351.943029317208 | 8.153317508143669 |
2017-05 | 34073 | 33599.270800927814 | 9.333130778035503 |
2017-06 | 61925 | 35400.11262010486 | 9.833364616695794 |
2017-07 | 44485 | 44070.653793413476 | 12.241848275948188 |
2017-08 | 38466 | 30320.607263557435 | 8.422390906543733 |
2017-09 | 31954 | 30141.586436752805 | 8.372662899098001 |
2017-10 | 54046 | 27575.77075084184 | 7.659936319678288 |
2017-11 | 87467 | 26761.449563835475 | 7.4337359899542985 |
2017-12 | 42113 | 32499.155343955306 | 9.027543151098696 |
2018-01 | 518 | 29127.7335907336 | 8.09103710853711 |
I think we need a plot of this data.
I'd also suggested using the geometric mean for looking at time-to-revert. E.g. geometric_mean = function(x){ exp(mean(log(x))) }
In python, I'd do:
>>> from statistics import mean >>> from math import log, exp >>> >>> def geo_mean(x): ... return exp(mean(log(x_val) for x_val in x)) ... >>> >>> mean([1,2,3,4,5,6]) 3.5 >>> geo_mean([1,2,3,4,5,6]) 2.993795165523909 >>> mean([1, 100, 2, 3, 76, 88]) 45 >>> geo_mean([1, 100, 2, 3, 76, 88]) 12.605921135923992
This is the new data:
Month | Number | Average (hour) | first quartile (hour) | median (hour) | last quartile (hour) | Geo mean (seconds) |
2013-02 | 6821 | 2.1991468341233773 | 0.00527777777778 | 0.0216666666667 | 0.151944444444 | 132.86284580032776 |
2013-03 | 17917 | 2.8346632775824325 | 0.0102777777778 | 0.0561111111111 | 0.539166666667 | 321.6465459454957 |
2013-04 | 34762 | 7.8544935721637295 | 0.00666666666667 | 0.759722222222 | 8.64027777778 | 1085.6034573069921 |
2013-05 | 32516 | 11.01927656128265 | 0.0825 | 4.93055555556 | 19.1100694444 | 4761.213122588603 |
2013-06 | 24598 | 7.892222425490781 | 0.353680555556 | 2.09916666667 | 15.7945833333 | 4825.439276953202 |
2013-07 | 7555 | 7.029551621442753 | 0.0127777777778 | 0.188333333333 | 5.74958333333 | 929.3304425969944 |
2013-08 | 8052 | 6.172952786057294 | 0.0172222222222 | 0.24625 | 5.33756944444 | 1036.062441273601 |
2013-09 | 7114 | 4.9773944959860055 | 0.0183333333333 | 0.245138888889 | 3.665 | 925.7537805061206 |
2013-10 | 9260 | 11.560696514278858 | 0.0190972222222 | 0.673194444444 | 16.8545138889 | 1740.5125758122417 |
2013-11 | 10504 | 6.883337987644919 | 0.0211111111111 | 0.473055555556 | 8.48506944444 | 1353.9937700205217 |
2013-12 | 15180 | 16.31476143683209 | 0.0847222222222 | 6.01055555556 | 35.0089583333 | 6189.446694505918 |
2014-01 | 14679 | 13.647583414704302 | 0.0619444444444 | 2.14694444444 | 30.0533333333 | 4273.771618016276 |
2014-02 | 17485 | 5.993416690496616 | 0.0338888888889 | 0.540277777778 | 4.63694444444 | 1399.4303378428422 |
2014-03 | 12631 | 5.632182065289103 | 0.0236111111111 | 0.453888888889 | 5.76013888889 | 1323.240246068031 |
2014-04 | 12520 | 7.185814474618389 | 0.0263888888889 | 0.554861111111 | 9.00458333333 | 1640.7044790992202 |
2014-05 | 15133 | 10.307204288640719 | 0.0413888888889 | 2.02472222222 | 19.0961111111 | 3174.742202212586 |
2014-06 | 19371 | 11.944432872162855 | 0.0615277777778 | 3.22138888889 | 22.2073611111 | 4228.159227770243 |
2014-07 | 34054 | 17.099208479343265 | 0.140555555556 | 12.1006944444 | 33.4865972222 | 6291.251250359374 |
2014-08 | 15098 | 11.518342293313315 | 0.0505555555556 | 3.49458333333 | 20.9404861111 | 3833.1045376465695 |
2014-09 | 11549 | 7.718344902396552 | 0.0127777777778 | 0.796666666667 | 8.52111111111 | 1057.2491634998469 |
2014-10 | 13161 | 10.263731078354397 | 0.104722222222 | 4.39722222222 | 17.5827777778 | 4853.667500504064 |
2014-11 | 34496 | 19.482995081555348 | 4.50513888889 | 22.10625 | 28.3934027778 | 21719.050783607843 |
2014-12 | 16044 | 7.542047580957921 | 0.0544444444444 | 1.02208333333 | 9.06951388889 | 2290.8116706971905 |
2015-01 | 23252 | 10.102309144255214 | 0.0805555555556 | 1.43944444444 | 13.2475694444 | 3350.2806461362784 |
2015-02 | 21412 | 7.1939816587790855 | 0.0588888888889 | 0.651388888889 | 7.31041666667 | 2060.9280488912323 |
2015-03 | 27340 | 13.225668434528163 | 0.105 | 2.54138888889 | 31.1161805556 | 4996.953295070048 |
2015-04 | 30730 | 17.606195728025455 | 0.825902777778 | 14.1227777778 | 30.2775 | 13399.019492677255 |
2015-05 | 14039 | 12.025643999651765 | 0.0580555555556 | 2.26444444444 | 23.8316666667 | 3857.3118494680843 |
2015-06 | 14073 | 8.165073209534413 | 0.0330555555556 | 0.749444444444 | 10.8336111111 | 1905.6095435477175 |
2015-07 | 18497 | 11.716545535912731 | 0.0875 | 2.74361111111 | 22.2741666667 | 4284.532531253856 |
2015-08 | 17770 | 11.932963327705872 | 0.0572222222222 | 1.95888888889 | 23.3471527778 | 3721.9030917244063 |
2015-09 | 18581 | 7.670950732229458 | 0.0494444444444 | 1.11944444444 | 9.69555555556 | 2352.5438921601585 |
2015-10 | 26106 | 9.724980528103373 | 0.0691666666667 | 1.99444444444 | 16.3405555556 | 3431.9107897312483 |
2015-11 | 45213 | 15.011060271505 | 0.246944444444 | 3.8275 | 28.3911111111 | 5573.570488066568 |
2015-12 | 28413 | 11.780431609943806 | 0.0816666666667 | 2.56361111111 | 23.0080555556 | 4132.71109472196 |
2016-01 | 44766 | 16.79404371869524 | 0.432222222222 | 14.7036111111 | 31.6809722222 | 10813.405643138178 |
2016-02 | 23914 | 7.30484723035321 | 0.0453472222222 | 0.647222222222 | 7.54131944444 | 1943.457141571479 |
2016-03 | 27758 | 6.758088599082547 | 0.0697222222222 | 0.770277777778 | 9.60395833333 | 2410.452891434275 |
2016-04 | 30416 | 10.227660377944357 | 0.133541666667 | 3.32569444444 | 17.6611805556 | 4972.091989111171 |
2016-05 | 21610 | 7.005441950742969 | 0.0277777777778 | 0.527777777778 | 6.04305555556 | 1506.158973248446 |
2016-06 | 23020 | 7.655243133989767 | 0.0541666666667 | 1.21430555556 | 7.88798611111 | 2356.769406591105 |
2016-07 | 31846 | 8.057065103239898 | 0.0897222222222 | 1.29625 | 6.07784722222 | 2542.8589566948995 |
2016-08 | 18751 | 6.463447564278053 | 0.0211111111111 | 0.553611111111 | 6.46736111111 | 1354.002299741235 |
2016-09 | 23275 | 6.830751533595895 | 0.0372222222222 | 0.832222222222 | 10.2781944444 | 1839.9137458364835 |
2016-10 | 31125 | 8.03764581883088 | 0.0813888888889 | 1.65666666667 | 11.1947222222 | 2858.483665156888 |
2016-11 | 25024 | 6.828695119352089 | 0.0447222222222 | 0.850833333333 | 7.94972222222 | 2000.6514309612098 |
2016-12 | 26135 | 10.68728651446549 | 0.0466666666667 | 1.60472222222 | 18.06625 | 2982.7133700511777 |
2017-01 | 60342 | 21.721567753619187 | 0.605625 | 18.8195833333 | 43.1910416667 | 13661.402602844963 |
2017-02 | 35700 | 8.080320020230314 | 0.0161111111111 | 0.657777777778 | 8.55388888889 | 1372.9292490882046 |
2017-03 | 48801 | 8.826341109813324 | 0.0519444444444 | 1.34361111111 | 12.1497222222 | 2719.2814204540837 |
2017-04 | 27049 | 8.153317508143656 | 0.0361111111111 | 0.888888888889 | 9.54 | 2026.0390930816654 |
2017-05 | 34073 | 9.333130778035395 | 0.0372222222222 | 0.733611111111 | 17.1202777778 | 1996.5815620862377 |
2017-06 | 61925 | 9.833364616695825 | 0.0219444444444 | 3.52111111111 | 23.3766666667 | 2184.1250102359068 |
2017-07 | 44485 | 12.241848275948197 | 0.0116666666667 | 0.953055555556 | 14.2180555556 | 1386.5594154053178 |
2017-08 | 38466 | 8.422390906543729 | 0.0584027777778 | 1.80902777778 | 9.99465277778 | 2832.105630765698 |
2017-09 | 31954 | 8.372662899098009 | 0.0472222222222 | 1.83152777778 | 9.99805555556 | 2682.296850277629 |
2017-10 | 54068 | 7.668291523842404 | 0.0788888888889 | 2.86527777778 | 8.93118055556 | 3174.2841649084194 |
2017-11 | 87467 | 7.433713124187789 | 1.10083333333 | 2.98388888889 | 7.57902777778 | 6615.386286727896 |
2017-12 | 42113 | 9.027543151098763 | 0.0322222222222 | 1.49083333333 | 16.9333333333 | 2610.847848926223 |
2018-01 | 518 | 8.091037108537108 | 0.0311805555556 | 0.545138888889 | 12.1175 | 2030.5197775763806 |
Another data:
Month | Number of users reverting | Average number of reverts per user | First quartile | median | last quartile |
2013-03 | 1198 | 10.473288814691152 | 1.0 | 1.0 | 4.0 |
2013-04 | 1133 | 19.50397175639894 | 1.0 | 2.0 | 4.0 |
2013-05 | 1153 | 15.333044232437121 | 1.0 | 2.0 | 4.0 |
2013-06 | 1134 | 12.961199294532628 | 1.0 | 1.0 | 3.0 |
2013-07 | 830 | 5.760240963855422 | 1.0 | 1.0 | 3.0 |
2013-08 | 828 | 5.929951690821256 | 1.0 | 1.0 | 3.0 |
2013-09 | 678 | 6.020648967551622 | 1.0 | 1.0 | 3.0 |
2013-10 | 831 | 6.439229843561973 | 1.0 | 1.0 | 3.0 |
2013-11 | 950 | 6.95578947368421 | 1.0 | 1.5 | 4.0 |
2013-12 | 1160 | 7.764655172413793 | 1.0 | 1.0 | 3.0 |
2014-01 | 1370 | 6.793430656934307 | 1.0 | 1.0 | 3.0 |
2014-02 | 1305 | 8.224521072796934 | 1.0 | 1.0 | 3.0 |
2014-03 | 1430 | 6.046153846153846 | 1.0 | 1.0 | 3.0 |
2014-04 | 1437 | 5.627000695894224 | 1.0 | 1.0 | 3.0 |
2014-05 | 1465 | 6.653242320819112 | 1.0 | 1.0 | 3.0 |
2014-06 | 1387 | 10.374909877433309 | 1.0 | 1.0 | 3.0 |
2014-07 | 1271 | 16.61369000786782 | 1.0 | 1.0 | 3.0 |
2014-08 | 1284 | 7.235981308411215 | 1.0 | 1.0 | 3.0 |
2014-09 | 961 | 8.49219562955255 | 1.0 | 1.0 | 3.0 |
2014-10 | 1028 | 8.092412451361868 | 1.0 | 1.0 | 3.0 |
2014-11 | 1109 | 25.963931469792605 | 1.0 | 1.0 | 3.0 |
2014-12 | 1307 | 8.651874521805661 | 1.0 | 1.0 | 3.0 |
2015-01 | 1576 | 8.96256345177665 | 1.0 | 1.0 | 3.0 |
2015-02 | 1543 | 8.955930006480882 | 1.0 | 1.0 | 3.0 |
2015-03 | 1692 | 9.546690307328605 | 1.0 | 1.0 | 3.0 |
2015-04 | 1602 | 12.559925093632959 | 1.0 | 1.0 | 3.0 |
2015-05 | 1308 | 6.4984709480122325 | 1.0 | 1.0 | 3.0 |
2015-06 | 1437 | 5.907446068197634 | 1.0 | 1.0 | 3.0 |
2015-07 | 1555 | 5.819935691318328 | 1.0 | 1.0 | 3.0 |
2015-08 | 1781 | 6.595171252105558 | 1.0 | 1.0 | 3.0 |
2015-09 | 1731 | 6.52686308492201 | 1.0 | 1.0 | 3.0 |
2015-10 | 1783 | 9.151430173864274 | 1.0 | 1.0 | 3.0 |
2015-11 | 1771 | 14.502540937323547 | 1.0 | 1.0 | 3.0 |
2015-12 | 1876 | 10.396588486140725 | 1.0 | 1.0 | 3.0 |
2016-01 | 2078 | 13.617901828681424 | 1.0 | 1.0 | 3.0 |
2016-02 | 2040 | 7.348039215686274 | 1.0 | 1.0 | 3.0 |
2016-03 | 2033 | 9.179045745204132 | 1.0 | 1.0 | 3.0 |
2016-04 | 1976 | 10.891194331983806 | 1.0 | 1.0 | 3.0 |
2016-05 | 2041 | 6.458108770210681 | 1.0 | 1.0 | 3.0 |
2016-06 | 1991 | 7.016574585635359 | 1.0 | 1.0 | 3.0 |
2016-07 | 2059 | 9.47887323943662 | 1.0 | 1.0 | 3.0 |
2016-08 | 1632 | 6.544117647058823 | 1.0 | 1.0 | 3.0 |
2016-09 | 1683 | 8.282234105763518 | 1.0 | 2.0 | 3.0 |
2016-10 | 1866 | 10.188638799571276 | 1.0 | 1.0 | 3.0 |
2016-11 | 1977 | 7.801213960546282 | 1.0 | 1.0 | 3.0 |
2016-12 | 1962 | 8.120285423037716 | 1.0 | 1.0 | 3.0 |
2017-01 | 2290 | 10.577729257641922 | 1.0 | 1.0 | 3.0 |
2017-02 | 2177 | 9.859439595774 | 1.0 | 1.0 | 3.0 |
2017-03 | 2374 | 12.600252737994944 | 1.0 | 1.0 | 4.0 |
2017-04 | 1862 | 7.81203007518797 | 1.0 | 1.0 | 3.0 |
2017-05 | 2029 | 10.611138491867916 | 1.0 | 1.0 | 3.0 |
2017-06 | 2091 | 24.705882352941178 | 1.0 | 1.0 | 3.0 |
2017-07 | 2325 | 10.858494623655915 | 1.0 | 1.0 | 3.0 |
2017-08 | 2338 | 9.887082976903336 | 1.0 | 2.0 | 3.0 |
2017-09 | 2323 | 7.921222557038313 | 1.0 | 2.0 | 3.0 |
2017-10 | 2444 | 13.107610474631752 | 1.0 | 2.0 | 4.0 |
2017-11 | 2575 | 18.28504854368932 | 1.0 | 2.0 | 4.0 |
2017-12 | 2524 | 9.716719492868462 | 1.0 | 1.0 | 3.0 |
2018-01 | 111 | 2.963963963963964 | 1.0 | 1.0 | 2.0 |
(Same structure but for users who have reverted more than five edits per month)
Month | Number of users reverting | Average number of reverts per user | First quartile | median | last quartile |
2013-02 | 114 | 34.90350877192982 | 8.0 | 13.0 | 25.0 |
2013-03 | 215 | 50.730232558139534 | 8.0 | 15.0 | 33.5 |
2013-04 | 201 | 101.68159203980099 | 9.0 | 13.0 | 35.0 |
2013-05 | 209 | 76.77990430622009 | 8.0 | 15.0 | 32.0 |
2013-06 | 173 | 75.76300578034682 | 8.0 | 13.0 | 31.0 |
2013-07 | 146 | 25.23972602739726 | 7.25 | 12.0 | 25.0 |
2013-08 | 141 | 27.085106382978722 | 8.0 | 12.0 | 30.0 |
2013-09 | 111 | 28.27027027027027 | 8.0 | 14.0 | 30.5 |
2013-10 | 146 | 29.054794520547944 | 8.0 | 11.0 | 24.75 |
2013-11 | 162 | 32.48765432098765 | 8.0 | 14.0 | 30.75 |
2013-12 | 158 | 46.563291139240505 | 8.0 | 13.0 | 27.0 |
2014-01 | 160 | 45.8625 | 8.0 | 13.0 | 21.25 |
2014-02 | 173 | 51.47398843930636 | 8.0 | 14.0 | 33.0 |
2014-03 | 161 | 40.857142857142854 | 9.0 | 14.0 | 34.0 |
2014-04 | 162 | 37.135802469135804 | 8.0 | 13.0 | 33.75 |
2014-05 | 196 | 39.295918367346935 | 7.0 | 12.0 | 22.0 |
2014-06 | 194 | 64.14948453608247 | 8.25 | 14.0 | 32.75 |
2014-07 | 189 | 102.63492063492063 | 8.0 | 15.0 | 33.0 |
2014-08 | 172 | 43.45348837209303 | 8.0 | 12.0 | 25.5 |
2014-09 | 134 | 50.798507462686565 | 8.0 | 13.0 | 28.0 |
2014-10 | 150 | 46.04 | 8.0 | 14.0 | 31.0 |
2014-11 | 166 | 164.51807228915663 | 8.0 | 13.0 | 34.75 |
2014-12 | 182 | 52.120879120879124 | 8.0 | 12.0 | 32.0 |
2015-01 | 211 | 56.43601895734597 | 8.0 | 14.0 | 34.0 |
2015-02 | 205 | 56.94146341463415 | 8.0 | 14.0 | 35.0 |
2015-03 | 235 | 58.46808510638298 | 8.0 | 13.0 | 32.0 |
2015-04 | 217 | 82.24884792626727 | 7.0 | 11.0 | 27.0 |
2015-05 | 171 | 38.98830409356725 | 7.0 | 11.0 | 26.0 |
2015-06 | 188 | 34.20744680851064 | 7.0 | 11.0 | 23.25 |
2015-07 | 194 | 34.9639175257732 | 8.0 | 12.0 | 26.0 |
2015-08 | 230 | 39.80434782608695 | 8.0 | 10.0 | 23.0 |
2015-09 | 250 | 34.78 | 7.0 | 11.0 | 21.0 |
2015-10 | 290 | 47.5 | 8.0 | 13.0 | 25.75 |
2015-11 | 272 | 84.99632352941177 | 7.0 | 12.0 | 27.0 |
2015-12 | 279 | 60.11469534050179 | 7.0 | 12.0 | 24.0 |
2016-01 | 310 | 81.48387096774194 | 8.0 | 12.0 | 29.75 |
2016-02 | 314 | 38.503184713375795 | 8.0 | 12.0 | 22.0 |
2016-03 | 326 | 48.20245398773006 | 7.0 | 12.0 | 23.0 |
2016-04 | 313 | 59.77316293929712 | 7.0 | 11.0 | 25.0 |
2016-05 | 315 | 32.37777777777778 | 7.5 | 11.0 | 23.0 |
2016-06 | 322 | 34.52795031055901 | 7.0 | 11.0 | 24.75 |
2016-07 | 315 | 52.55873015873016 | 8.0 | 13.0 | 23.0 |
2016-08 | 245 | 34.03265306122449 | 7.0 | 11.0 | 23.0 |
2016-09 | 263 | 43.53231939163498 | 8.0 | 13.0 | 26.0 |
2016-10 | 278 | 58.726618705035975 | 8.0 | 11.5 | 25.0 |
2016-11 | 279 | 44.6415770609319 | 7.0 | 11.0 | 27.0 |
2016-12 | 304 | 43.01315789473684 | 7.0 | 12.0 | 24.0 |
2017-01 | 354 | 58.91242937853107 | 8.0 | 12.0 | 29.0 |
2017-02 | 343 | 53.57434402332362 | 8.0 | 12.0 | 25.0 |
2017-03 | 399 | 66.40350877192982 | 8.0 | 12.0 | 28.0 |
2017-04 | 279 | 42.473118279569896 | 7.0 | 13.0 | 29.5 |
2017-05 | 322 | 57.857142857142854 | 8.0 | 12.0 | 28.0 |
2017-06 | 340 | 143.38823529411764 | 8.0 | 13.0 | 32.0 |
2017-07 | 372 | 58.895161290322584 | 7.0 | 12.0 | 25.0 |
2017-08 | 377 | 52.206896551724135 | 7.0 | 12.0 | 26.0 |
2017-09 | 380 | 39.48421052631579 | 7.0 | 12.0 | 25.0 |
2017-10 | 428 | 66.61915887850468 | 7.0 | 12.0 | 28.0 |
2017-11 | 434 | 99.97235023041475 | 8.0 | 12.0 | 27.75 |
2017-12 | 403 | 51.67245657568238 | 8.0 | 14.0 | 28.0 |
2018-01 | 12 | 15.75 | 7.0 | 10.0 | 20.0 |
We discussed getting the plots cleaned up and adding English/Spanish Wikipedia at our sync meeting.
This is great. Please graph the results, write a report, and give a description of the weirdness in Spanish's dump files.
This is the plot of geographical mean of revert time in Wikidata:
This is median of reverts made by users who made more than five reverts in that month
This is number of users who reverted more than five in the month:
Started this: https://meta.wikimedia.org/wiki/Research:Revert_time_analysis
Will work on it more in the next couple of days.
OK I made an epic to cover other work we should do before we speak publicly about what we found. See T200898: Analyze the effects of ORES deployments on counter-vandalism behavior
I think this will make for a great follow-up paper to When the Levee Breaks. But more immediately, we'll get a better view of what counter-vandalism looks like on various wikis.
Oh! And to the point of reviewing this specific task, please limit your aggregate analysis to 12 months. This will help account for seasonality. E.g., December/January and September look weird and can appear twice in a 17 month sample.