Now that you've learned how to translate between different natural languages, let's take a look at an example of something that's even simpler: classifying sentences into categories.
For example, let's say that you're trying to analyze the sentiments of people on Twitter. But let's be a bit more specific: you're a data scientist working for an airline, and you want to see how people are reacting to your brand on social media. There are two difficulties here:
- Social media is a complex ecosystem; each platform has its own share of people, often of different demographics, and therefore, a different culture around that platform. On Twitter, you'll see lots of hashtags, people tweeting about things that are trending, abbreviations, and more, that are specific to, or at least most prominent on, the Twitter platform.
- People speak differently about airlines than they do about, say, a grocery store. They use different words, hashtags, and emojis. This...