Systems and methods for determining whether to publish an advertisement on a web page associated with a web page article or to exclude advertisements from publication on the web page associated with the web page article based on the comparison of a first numeric likelihood to a first set of threshold values

1. A computer-executable method for managing publication of a web page article using a computing device, the method comprising:

using a trained machine learning system implementing a machine learning algorithm embodied on one or more computer-readable media, processing the web page article to generate a first numeric likelihood that the web page article is associated with a first selected category of web page articles unsuitable for accompaniment with advertising;

comparing, using the computing device, the first numeric likelihood to a first set of one or more threshold values associated with the first selected category; and

determining, using the computing device, whether to publish an advertisement on a web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article based on the comparison of the first numeric likelihood to the first set of threshold values.

2. The method of claim 1 , wherein the processing of the web page article comprises:

parsing textual content of the web page article into a sequence of n-grams; and

analyzing the sequence of n-grams using the trained machine learning system to generate the first numeric likelihood.

3. The method of claim 1 , wherein the first set of threshold values includes a first threshold and a second threshold, the first threshold being smaller in magnitude than the second threshold.

4. The method of claim 3 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that the advertisement can be automatically published on the web page associated with the advertisement if the first numeric likelihood is smaller in magnitude than the first threshold.

5. The method of claim 4 , further comprising:

automatically publishing the advertisement on the web page associated with the web page article if the first numeric likelihood is smaller in magnitude than the first threshold.

6. The method of claim 3 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that advertisements can be automatically excluded from publication on the web page associated with the web page article if the first numeric likelihood is greater in magnitude than the second threshold.

7. The method of claim 6 , further comprising:

automatically publishing the web page article without the advertisement if the first numeric likelihood is greater in magnitude than the second threshold.

8. The method of claim 3 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that all advertisements can be automatically excluded from publication on the web page article if the first numeric likelihood is greater in magnitude than the second threshold.

9. The method of claim 8 , further comprising:

automatically excluding all advertisements from publication on the web page article upon determination that the first numeric likelihood is greater in magnitude than the second threshold.

10. The method of claim 3 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

taking an action to perform a review of the web page article if the first numeric likelihood falls between the first threshold and the second threshold.

11. The method of claim 1 , further comprising:

analyzing the web page article to generate a second numeric likelihood that the web page article falls into a second selected category of web page articles unsuitable for accompaniment with the advertisement, the analyzing comprising analyzing the sequence of n-grams using a trained machine learning system implementing a machine learning algorithm embodied on one or more computer-readable media to generate the second numeric likelihood;

comparing the second numeric likelihood to a second set of threshold values associated with the second selected category; and

automatically determining whether to publish an advertisement on the web page article or to exclude advertisements from publication on the web page article based on the comparison of the first numeric likelihood to the first set of threshold values and the comparison of the second numeric likelihood to the second set of threshold values.

12. The method of claim 11 , wherein:

the first set of threshold values includes a first threshold and a second threshold, the first threshold being smaller in magnitude than the second threshold; and

the second set of threshold values includes a third threshold and a fourth threshold, the third threshold being smaller in magnitude than the second threshold.

13. The method of claim 12 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that the advertisement can be automatically published on the web page article if the first numeric likelihood is smaller in magnitude than the first threshold corresponding to the first selected category and if the second numeric likelihood is smaller in magnitude than the third threshold corresponding to the second selected category.

14. The method of claim 12 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that the advertisement can be automatically excluded from publication on the web page article if the first numeric likelihood is greater in magnitude than the second threshold corresponding to the first selected category or if the second numeric likelihood is greater in magnitude than the fourth threshold corresponding to the second selected category.

15. The method of claim 12 , wherein the first set of threshold values includes a first threshold and the second set of threshold values includes a second threshold, and wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

automatically excluding the advertisement from publication on the web page article upon determination that the first numeric likelihood is greater in magnitude than the first threshold corresponding to the first selected category and the second numeric likelihood is greater in magnitude than the second threshold corresponding to the second selected category.

16. The method of claim 12 , wherein the first set of threshold values includes a first threshold and the second set of threshold values includes a second threshold, and wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

automatically publishing the advertisement on the web page article upon determination that the first numeric likelihood is smaller in magnitude than the first threshold corresponding to the first selected category and the second numeric likelihood is smaller in magnitude than the second threshold corresponding to the second selected category.

17. The method of claim 1 , wherein the machine learning system is trained using a boosting system implementing a boosting algorithm embodied on a computer-readable medium.

18. The method of claim 1 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude the advertisement from publication on the web page associated with the web page article comprises:

determining a category of textual content of the advertisement; and

determining whether the web page article is suitable for accompaniment with the advertisement based on:

the comparison of the first numeric likelihood to the first set of threshold values, and

the category of the textual content of the advertisement.

19. A computer-executable method for managing publication of a web page article using a computing device, the method comprising the following operations performed by at least one processor:

selecting an advertisement for publication on a web page associated with the web page article;

generating a first numeric likelihood that the web page article is associated with a first selected category of web page articles unsuitable for accompaniment with advertising;

comparing the first numeric likelihood to a first set of one or more threshold values associated with the first selected category; and

determining whether to publish the advertisement on the web page associated with the web page article or to exclude the advertisement from publication on the web page associated with the web page article based on the comparison of the first numeric likelihood to the first set of threshold values.

20. The method of claim 19 , wherein the method further comprises reviewing a tag associated with the web page article, the tag indicating that the web page article is associated with the first selected category of web page articles unsuitable for accompaniment with advertising, and wherein the method further comprises:

automatically excluding the advertisement from publication on the web page associated with the web page article based on the reviewing of the tag associated with the web page article.

21. The method of claim 19 , wherein the method further comprises reviewing a tag associated with the web page article, the tag indicating that the web page article is associated with a first selected category of web page articles suitable for accompaniment with advertising, and wherein the method further comprises:

automatically publishing the advertisement on the web page associated with the web page article based on the reviewing of the tag associated with the web page article.

22. The method of claim 19 , wherein the method further comprises reviewing a tag associated with the web page article, the tag indicating a second numeric likelihood that the web page article is associated with a second selected category of web page articles unsuitable for accompaniment with advertising, and wherein the method further comprises:

comparing the second numeric likelihood to a second set of one or more threshold values associated with the second selected category; and

determining whether to publish the advertisement on the web page associated with the web page article or to exclude the advertisement from publication on the web page associated with the web page article based on the comparison of the second numeric likelihood to the second set of threshold values.

23. The method of claim 19 , wherein generating the first numeric likelihood comprises: parsing textual content of the web page article into a sequence of n-grams, and analyzing the sequence of n-grams using a trained machine learning system implementing a machine learning algorithm embodied on one or more computer-readable media to generate the first numeric likelihood.

24. The method of claim 19 , further comprising:

reviewing a tag associated with the advertisement, the tag indicating that the advertisement is associated with a first selected category of advertisements; and

automatically determining whether to publish the advertisement on the web page associated with the web page article based on the reviewing of the tag associated with the web page article and the tag associated with the advertisement.

25. A non-transitory computer-readable medium encoded with computer-executable instructions for performing a method for managing publication of a web page article using a computing device, the method comprising:

using a trained machine learning system implementing a machine learning algorithm embodied on one or more computer-readable media, processing the web page article to generate a first numeric likelihood that the web page article is associated with a first selected category of web page articles unsuitable for accompaniment with advertising; comparing, using the computing device, the first numeric likelihood to a first set of one or more threshold values associated with the first selected category; and

determining, using the computing device, whether to publish an advertisement on a web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article based on the comparison of the first numeric likelihood to the first set of threshold values.

26. The computer-readable medium of claim 25 , wherein the processing of the web page article comprises:

parsing textual content of the web page article into a sequence of n-grams; and

analyzing the sequence of n-grams using the trained machine learning system to generate the first numeric likelihood.

27. The computer-readable medium of claim 25 , wherein the first set of threshold values includes a first threshold and a second threshold, the first threshold being smaller in magnitude than the second threshold.

28. The computer-readable medium of claim 27 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that the advertisement can be automatically published on the web page associated with the advertisement if the first numeric likelihood is smaller in magnitude than the first threshold.

29. The computer-readable medium of claim 28 , wherein the method further comprises:

automatically publishing the advertisement on the web page associated with the web page article if the first numeric likelihood is smaller in magnitude than the first threshold.

30. The computer-readable medium of claim 27 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that advertisements can be automatically excluded from publication on the web page associated with the web page article if the first numeric likelihood is greater in magnitude than the second threshold.

31. The computer-readable medium of claim 30 , wherein the method further comprises:

automatically publishing the web page article without the advertisement if the first numeric likelihood is greater in magnitude than the second threshold.

32. The computer-readable medium of claim 27 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that all advertisements can be automatically excluded from publication on the web page article if the first numeric likelihood is greater in magnitude than the second threshold.

33. The computer-readable medium of claim 32 , wherein the method further comprises:

automatically excluding all advertisements from publication on the web page article upon determination that the first numeric likelihood is greater in magnitude than the second threshold.

34. The computer-readable medium of claim 27 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

taking an action to perform a review of the web page article if the first numeric likelihood falls between the first threshold and the second threshold.

35. The computer-readable medium of claim 25 , wherein the method further comprises:

analyzing the web page article to generate a second numeric likelihood that the web page article falls into a second selected category of web page articles unsuitable for accompaniment with the advertisement, the analyzing comprising analyzing the sequence of n-grams using a trained machine learning system implementing a machine learning algorithm embodied on one or more computer-readable media to generate the second numeric likelihood;

comparing the second numeric likelihood to a second set of threshold values associated with the second selected category; and

automatically determining whether to publish an advertisement on the web page article or to exclude advertisements from publication on the web page article based on the comparison of the first numeric likelihood to the first set of threshold values and the comparison of the second numeric likelihood to the second set of threshold values.

36. The computer-readable medium of claim 35 , wherein:

the first set of threshold values includes a first threshold and a second threshold, the first threshold being smaller in magnitude than the second threshold; and

the second set of threshold values includes a third threshold and a fourth threshold, the third threshold being smaller in magnitude than the second threshold.

37. The computer-readable medium of claim 36 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that the advertisement can be automatically published on the web page article if the first numeric likelihood is smaller in magnitude than the first threshold corresponding to the first selected category and if the second numeric likelihood is smaller in magnitude than the third threshold corresponding to the second selected category.

38. The computer-readable medium of claim 36 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

determining that the advertisement can be automatically excluded from publication on the web page article if the first numeric likelihood is greater in magnitude than the second threshold corresponding to the first selected category or if the second numeric likelihood is greater in magnitude than the fourth threshold corresponding to the second selected category.

39. The computer-readable medium of claim 36 , wherein the first set of threshold values includes a first threshold and the second set of threshold values includes a second threshold, and wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

automatically excluding the advertisement from publication on the web page article upon determination that the first numeric likelihood is greater in magnitude than the first threshold corresponding to the first selected category and the second numeric likelihood is greater in magnitude than the second threshold corresponding to the second selected category.

40. The computer-readable medium of claim 36 , wherein the first set of threshold values includes a first threshold and the second set of threshold values includes a second threshold, and wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude advertisements from publication on the web page associated with the web page article comprises:

automatically publishing the advertisement on the web page article upon determination that the first numeric likelihood is smaller in magnitude than the first threshold corresponding to the first selected category and the second numeric likelihood is smaller in magnitude than the second threshold corresponding to the second selected category.

41. The computer-readable medium of claim 25 , wherein the machine learning system is trained using a boosting system implementing a boosting algorithm embodied on a computer-readable medium.

42. The computer-readable medium of claim 25 , wherein the determining of whether to publish an advertisement on the web page associated with the web page article or to exclude the advertisement from publication on the web page associated with the web page article comprises:

determining a category of textual content of the advertisement; and

determining whether the web page article is suitable for accompaniment with the advertisement based on: the comparison of the first numeric likelihood to the first set of threshold values, and the category of the textual content of the advertisement.

43. A non-transitory computer-readable medium encoded with computer-executable instructions for performing a method for managing publication of a web page article using a computing device, the method comprising:

selecting an advertisement for publication on a web page associated with the web page article;

generating a first numeric likelihood that the web page article is associated with a first selected category of web page articles unsuitable for accompaniment with advertising;

comparing the first numeric likelihood to a first set of one or more threshold values associated with the first selected category; and

determining whether to publish the advertisement on the web page associated with the web page article or to exclude the advertisement from publication on the web page associated with the web page article based on the comparison of the first numeric likelihood to the first set of threshold values.

44. The computer-readable medium of claim 43 , wherein the method further comprises reviewing a tag associated with the web page article, the tag indicating that the web page article is associated with the first selected category of web page articles unsuitable for accompaniment with advertising, and wherein the method further comprises:

automatically excluding the advertisement from publication on the web page associated with the web page article based on the reviewing of the tag associated with the web page article.

45. The computer-readable medium of claim 43 , wherein the method further comprises reviewing a tag associated with the web page article, the tag indicating that the web page article is associated with a first selected category of web page articles suitable for accompaniment with advertising, and wherein the method further comprises:

automatically publishing the advertisement on the web page associated with the web page article based on the reviewing of the tag associated with the web page article.

46. The computer-readable medium of claim 43 , wherein the method further comprises reviewing a tag associated with the web page article, the tag indicating a second numeric likelihood that the web page article is associated with a second selected category of web page articles unsuitable for accompaniment with advertising, and wherein the method further comprises:

comparing the second numeric likelihood to a second set of one or more threshold values associated with the second selected category; and

determining whether to publish the advertisement on the web page associated with the web page article or to exclude the advertisement from publication on the web page associated with the web page article based on the comparison of the second numeric likelihood to the second set of threshold values.

47. The computer-readable medium of claim 43 , wherein generating the first numeric likelihood comprises parsing textual content of the web page article into a sequence of n-grams, and analyzing the sequence of n-grams using a trained machine learning system implementing a machine learning algorithm embodied on one or more computer-readable media to generate the first numeric likelihood.

48. The computer-readable medium of claim 43 , wherein the method further comprises:

reviewing a tag associated with the advertisement, the tag indicating that the advertisement is associated with a first selected category of advertisements; and automatically determining whether to publish the advertisement on the web page associated with the web page article based on the reviewing of the tag associated with the web page article and the tag associated with the advertisement.