Open Website

Testing and Issues

You can test this app and submit issues during the testing period of the Data Clustering Contest contest.

Entries with serious issues will not be able to win the contest, but even minor issues might be important for overall results.


by rating


Fair Leopard Feb 28, 2020 at 15:11
Final score for this submission (out of 100):

Languages: 13.25
News EN: 47.12
News RU: 13.23
Categories EN: 12.97
Categories RU: 13.13
Threads EN: 19.57
Threads RU: 9.73
Top news EN: 9.83
Top news RU: 7.74

These data reflect the relative accuracy, precision and speed of the algorithm as compared to the other submissions.
Fair Leopard Feb 6, 2020 at 16:03
In our preliminary tests, this submission received the following scores (out of 100):

Languages: 83
News EN: 85
News RU: 50
Categories EN: 44
Categories RU: 8
Threads EN: 55
Threads RU: 31
Top EN: 54
Top RU: 38

This is not the final result, please stay tuned for updates. We apologize for the delay.
Fair Mammoth Feb 7, 2020 at 20:39
В ходе предварительного тестирования алгоритма были выявлены следующие недостатки в ранжировании:

– Отсутствуют многие главные сюжеты в разделе ‘Main’ и внутри категорий. Нерелевантные сюжеты в топе. Не указаны категории в разделе 'Main'.

– Заголовки части сюжетов слишком размытые (информация не подаётся в краткой нейтральной форме).

– Нарушена сортировка статей во многих сюжетах: нерелевантные статьи отображаются выше релевантных.
Strange sience category
Modest Python Dec 12, 2019 at 21:22
I can't understand the results in Russian, I don't know the language. I'm very sorry :(
Looks like you have sever disbalance in classes - small amount of russan lang. detected, small amount of articles in society category
Modest Python Dec 12, 2019 at 22:04
As I replied to Suave Duck, I don't understand the Russian language so I can't tell easily if it's correct or not... Sorry!
Duplicate threads with identical content
Modest Python Dec 13, 2019 at 07:41
I understand this issue too. My submission recognizes those as similar news because it reads the content; I should have added a check that if two articles are too similar it discards them.
Threads flooded with similar news
Modest Python Dec 13, 2019 at 07:14
I understand the issue, thank you. This can be fixed by playing with the configuration file but of course now it's not possible :P
Yes, I understand, just explaining why I made my decision, so you won't be uncertain why you have unvotes
Modest Python Dec 12, 2019 at 22:06
Sure! I understand that. Good luck!
Nobody added any issues yet...