<aside> ➡️
A classifier adds classes or labels to data you have gathered. You do not have to create a classifier for Phoenix to work! You can skip this step and go straight to exploring your data. This section explains why you might want to create classifiers, and links to other sections with details on how to apply three different types of classifiers.
</aside>
Sometimes, the information you have about each post or comment you gathered will not be enough to make sense of trends or search for things that are useful to your problem statement. In this case, you might want to add a classification to your data. A classifier adds classes or labels to data you have gathered. In other words, the classifier adds another column to your data table containing information that is useful to you.
If you are interested in understanding trends in who posts, then you will want to classify the accounts (or authors) in your data. For example, you might want to classify accounts into categories relating to their profession, such as “academic,” “media,” or “politician.” Or you may want to organise them into categories relating to their position on an issue, such as “pro-army” or “anti-government”.
Note that you will add these classes from your own knowledge; the system just applies the information you provide it. In other words, the system doesn’t tell you who is “academic” or “media”, but rather you tell the system what accounts are “academic” or “media”, and then that class (or label) is applied to the data you have gathered.
Author classes will be added as a column to every row of the standard table. This means that you will be able to see, for example, how many posts are posted by each class of author, e.g. are there more posts by pro-army or anti-government authors.
<aside> ➡️ Jump to: post author classifier to learn how to classify authors in Phoenix.
</aside>
If you are interested in understanding trends in what is posted, then you will want to classify the text of posts or comments (or both).
One way to classify what is posted is to create classifications based on specific words or phrases that appear in the post or comment text. This kind of classification works well where we have a small list of keywords and phrases that are almost always associated with the class we are interested in. For example, this is useful when you want to classify text that contains hate speech, hashtags, group identifiers, specific events, and places.
A keyword text classifier will almost certainly get false positives and you will miss some posts. There may be some contexts where these issues will be overwhelming and the classification won’t be useful (e.g. some hate terms can have multiple uses, including in common parlance).
Getting to the list of keywords and features for each class will be the most time consuming part of this process, and may require iteration. You can try to apply a “lexicon” that someone else has already built, as a starting point.
<aside> ➡️ Jump to: keyword text classifier to learn how to classify posts and comments using keywords in Phoenix.
</aside>
The challenges of a text classification that relies only on a few keywords or features are, in summary, that the classification does not account for context. We can overcome this challenge to a certain extent by applying a classification that uses a large language model (or LLM). LLMs are trained on large amounts of data to learn how language works. They can then use this knowledge to perform a variety of natural language processing (NLP) tasks, including classifying text.
Put simply for our use case: you can train an LLM to identify when something is being said in a post or comment. LLMs are much better at classifying complicated things such as broad topics (”politics” or “gender”). They can also classify tone, for example identifying “intimidation” or “negative sentiment” or “toxicity”.
<aside> ➡️ Phoenix makes available a few complex models that you can apply to your data. Jump to: apply a complex model.
</aside>