METHODS, SYSTEMS, AND MEDIA FOR APPLYING SCORES AND RATINGS TO WEB PAGES,WEB SITES, AND CONTENT FOR SAFE AND EFFECTIVE ONLINE ADVERTISING
Systems, methods, and media for rating websites for safe advertising are provided. In accordance with some embodiments of the disclosed subject matter, the method comprises: extracting one or more features from a piece of web content; applying a plurality of statistical models to the extracted features to generate a plurality of ordinomial estimates, wherein each ordinomial estimate represents a probability that the web content is a member of one of a plurality of severity groups; determining a posterior ordinomial estimate for the web content by combining the plurality of ordinomial estimates; generating a risk rating that encodes severity and confidence based on the determined posterior ordinomial estimate, wherein the risk rating identifies whether the web content is likely to contain objectionable content of a given category; and providing the risk rating for determining whether an advertisement should be associated with the web content.
1 . A method for rating webpages for safe publication, the method comprising:
extracting features from a web page;
applying, using a hardware processor, a plurality of statistical models to the extracted features to generate a plurality of ordinomial estimates, wherein each ordinomial estimate represents a probability that the web page is a member of one of a plurality of severity groups;
generating a rating based on the plurality of ordinomial estimates; and
determining whether a content item should be published on the web page based on the rating.
2 . The method of claim 1 , wherein the content item is advertisement content.
3 . The method of claim 1 , further comprising determining a posterior ordinomial estimate for the web page by combining the plurality of ordinomial estimates.
4 . The method of claim 3 , further comprising:
determining a plurality of posterior ordinomial estimates at a plurality of times for the web page; and
determining an expected posterior ordinomial estimate by combining the plurality of posterior ordinomial estimates over the plurality of times.
5 . The method of claim 3 , further comprising:
determining that the web page belongs to a sitelet, wherein the sitelet includes at least one of a plurality of web pages;
determining a sitelet ordinomial by aggregating the plurality of posterior ordinomial estimates associated with the one or more web pages belonging to the sitelet; and
generating a sitelet rating based on the aggregated plurality of posterior ordinomials.
6 . The method of claim 1 , further comprising:
collecting a plurality of ratings associated with a plurality of web pages, wherein the plurality of ratings includes ordinal ratings and real-valued ratings;
determining an aggregate rating for the plurality of web pages based on the collected plurality of ratings;
normalizing the aggregate rating by mapping the aggregate rating to an index-scaled rating;
applying a severity weight to the index-scaled rating; and
generating a severity-weighted index-scaled rating for the plurality of web pages.
7 . The method of claim 1 , further comprising generating a combined rating by combining the generated rating that encodes whether the web page is likely to contain content of a first category with a second rating that encodes whether the web page is likely to contain content of a second category.
8 . A system for rating webpages for safe publication, the system comprising:
a hardware processor that:
extracts features from a web page;
applies a plurality of statistical models to the extracted features to generate a plurality of ordinomial estimates, wherein each ordinomial estimate represents a probability that the web page is a member of one of a plurality of severity groups;
generates a rating based on the plurality of ordinomial estimates; and
determines whether a content item should be published on the web page based on the rating.
9 . The system of claim 8 , wherein the content item is advertisement content.
10 . The system of claim 8 , wherein the hardware processor is further configured to determine a posterior ordinomial estimate for the web page by combining the plurality of ordinomial estimates.
11 . The system of claim 10 , wherein the hardware processor is further configured to:
determine a plurality of posterior ordinomial estimates at a plurality of times for the web page; and
determine an expected posterior ordinomial estimate by combining the plurality of posterior ordinomial estimates over the plurality of times.
12 . The system of claim 10 , wherein the hardware processor is further configured to:
determine that the web page belongs to a sitelet, wherein the sitelet includes at least one of a plurality of web pages;
determine a sitelet ordinomial by aggregating the plurality of posterior ordinomial estimates associated with the one or more web pages belonging to the sitelet; and
generate a sitelet rating based on the aggregated plurality of posterior ordinomials.
13 . The system of claim 8 , wherein the hardware processor is further configured to:
collect a plurality of ratings associated with a plurality of web pages, wherein the plurality of ratings includes ordinal ratings and real-valued ratings;
determine an aggregate rating for the plurality of web pages based on the collected plurality of ratings;
normalize the aggregate rating by mapping the aggregate rating to an index-scaled rating;
apply a severity weight to the index-scaled rating; and
generate a severity-weighted index-scaled rating for the plurality of web pages.
14 . The system of claim 8 , wherein the hardware processor is further configured to generate a combined rating by combining the generated rating that encodes whether the web page is likely to contain content of a first category with a second rating that encodes whether the web page is likely to contain content of a second category.
15 . A non-transitory computer-readable medium containing computer-executable instructions that, when executed by a processor, cause the processor to perform a method for rating webpages for safe publication, the method comprising:
16 . The non-transitory computer-readable medium of claim 15 , wherein the content item is advertisement content.
17 . The non-transitory computer-readable medium of claim 15 , wherein the method further comprises determining a posterior ordinomial estimate for the web page by combining the plurality of ordinomial estimates.
18 . The non-transitory computer-readable medium of claim 17 , wherein the method further comprises:
determining a plurality of posterior ordinomial estimates at a plurality of times for the web page; and
determining an expected posterior ordinomial estimate by combining the plurality of posterior ordinomial estimates over the plurality of times.
19 . The non-transitory computer-readable medium of claim 17 , wherein the method further comprises:
determining that the web page belongs to a sitelet, wherein the sitelet includes at least one of a plurality of web pages;
determining a sitelet ordinomial by aggregating the plurality of posterior ordinomial estimates associated with the one or more web pages belonging to the sitelet; and
generating a sitelet rating based on the aggregated plurality of posterior ordinomials.
20 . The non-transitory computer-readable medium of claim 15 , wherein the method further comprises:
collecting a plurality of ratings associated with a plurality of web pages, wherein the plurality of ratings includes ordinal ratings and real-valued ratings;
determining an aggregate rating for the plurality of web pages based on the collected plurality of ratings;
normalizing the aggregate rating by mapping the aggregate rating to an index-scaled rating;
applying a severity weight to the index-scaled rating; and
generating a severity-weighted index-scaled rating for the plurality of web pages.
21 . The non-transitory computer-readable medium of claim 15 , wherein the method further comprises generating a combined rating by combining the generated rating that encodes whether the web page is likely to contain content of a first category with a second rating that encodes whether the web page is likely to contain content of a second category.