Kids content tagger5/3/2023 ![]() You’ll work part-time at about 15 hours per week, and the position is expected to last one year.Īpply for the position here, and good luck!įind more work from home jobs in the directory. I’ve read that only 40 people worldwide hold the tagger position (that number might have slightly increased by now) add to that the fact that your job will be binge-watching TV from the cozy confines of home, and you can expect heavy competition for this position. The job posting only mentions that this position is “remote”, so hopefully that indicates that it is open to applicants across the United States. Our team is responsible for determining, across the United States and worldwide: 1) which content belongs in Kids profiles and how it evolves as kids grow up, and 2) tagging Kids shows and movies with an eye toward accuracy and consistency. The ideal candidate has in-depth knowledge of kids’ (ages 0–12) movies and television content. The tags help Netflix suggest additional shows to viewers based on their viewing history.įor example, the Netflix original show Stranger Things might be tagged with “science fiction”, “1980s”, and “conspiracy drama” along with other descriptions (If you’re a sci-fi fan, definitely give this show a look □ ).Īs a Kids Content Tagger, you will view content suitable for children up to age 12. Taggers watch shows and movies, and categorize or “tag” based on each programs’ characteristics. Please note that Netflix also has a general Tagger position that may be available again in the future. They may open the position again at a later date. That is, the learning algorithm will find similarities and cluster documents it considers similar, but the resulting clusters may not match your idea of what a 'good' class should contain.Netflix is no longer hiring for this position. ), or do you prefer to learn the set of classes from the data? Manual class labels may require more supervision (manual intervention), but if you choose to learn from the data, the 'labels' will likely not be meaningful to a human (e.g., class 1, class 2, etc.), and even the contents of the classes may not be terribly informative. consider an article discussing the economic outlook and its potential effect on the presidential race can that document belong partly to the 'economy' cluster and partly to the 'election' cluster? Some clustering algorithms allow partial class assignment and some do notĭo you want to create a set of classes manually (i.e., list out 'economy', 'sports'. You might also consider the agglomerative clustering implementations available in LingPipe (see ), although I suspect an LDA implementation might prove somewhat more reliable.Ī couple questions to consider while you're looking at clustering systems:ĭo you want to allow fractional class membership - e.g. I don't have personal experience with any of the LDA implementations available, so I can't recommend a specific system (perhaps others more knowledgeable than I might be able to recommend a user-friendly implementation). I'd recommend you look at Latent Direchlet Allocation () or 'LDA'. There are many possible choices of such algorithms, but this is an active area of research (meaning it is not a solved problem, and thus none of the algorithms are likely to perform quite as well as you'd like). ![]() This falls under the general category of 'clustering' algorithms. Kids Content Tagger at Netflix Milton-Freewater, Oregon, United States. Or if your classes are much finer-grained, the same articles might be assigned to 'Dallas Mavericks' and 'GOP Presidential Race'. For example, you might assign article 1 to 'Sports', article 2 to 'Politics', and so on. If I understand your question correctly, you'd like to group the articles into similarity classes. This also suffered from the problem of words or names that are split by space, for example if 1.000 articles contains the name "John Doe", and 1.000 articles contains the name of "John Hanson", I would only get the word "John" out of it, not his first name, and last name. When all the common words was filtered out, the only thing left is words that is tag-worthy.īut this turned out to be a rather manual task, and not a very pretty or helpful approach.Analyze them, and filter common non-descriptive words out like "them", "I", "this", "these", "their" etc.Get all words, remove all punctuation, split by space, and count them by occurrence.However, I also want to tag based on the article-text. So at least I can use the category to figure what type of content that we are working with. I am now searching for ways to help me tag these articles with somewhat descriptive tags.Īll these articles is accessible from a URL that looks like this: I am working with some really large databases of newspaper articles, I have them in a MySQL database, and I can query them all.
0 Comments
Leave a Reply. |