text classification
In plain wordsSorting pieces of text into categories automatically — what topic an article covers, whether a message is spam, which team should handle a customer's complaint.
The task of assigning one or more labels from a predefined set to a unit of text — a document, message, sentence or query — as in spam filtering, topic and genre labeling, sentiment analysissentiment analysis, n.: Using software to judge the feelings or opinions expressed in text — whether a review, post or comment is positive, negative or neutral, and about what., intent detection, language identification, and toxicity or policy-violation detection for content moderationcontent moderation, n.: Checking what people post, or what an AI produces, and removing, limiting or labeling whatever breaks the rules or the law — done by people, by AI, or by both together.. It may be binary, multiclassmulticlass classification, n.: Sorting each item into exactly one of three or more categories — for example, deciding which of the ten digits a handwritten number shows. or multilabelmultilabel classification, n.: Tagging each item with any number of labels at once — a photo can show a beach, a dog and a sunset — instead of picking just one category.. Classic pipelines represented text as a bag of wordsbag of words, n.: A simple way of turning text into numbers by counting how often each word appears and ignoring word order — like describing a recipe only by its shopping list. with TF-IDFTF-IDF, abbr.: A simple score for picking out the words that characterize a document: a word counts for more the more often it appears there, and for less the more of the collection's other documents also use it. weights and trained naive Bayesnaive Bayes, n.: A simple, fast way of sorting items into categories using probabilities, which pretends that each clue is independent of the others. It is the classic technique behind early email spam filters., logistic regressionlogistic regression, n.: A simple, widely used method for yes-or-no predictions that outputs a probability — say, a 70% chance a customer cancels — by passing a weighted sum of inputs through an S-shaped curve. or support vector machinessupport vector machine, n.: A classic method that separates two groups of examples with the widest possible gap — like laying the broadest possible road between them. A mathematical shortcut lets it draw curved boundaries too.; neural approaches used convolutional and recurrent networks and then fine-tuned transformer encoders. LLMs can now classify zero-shot from label descriptions, though fine-tuned small encoders often remain cheaper and more consistent at scale.
A fine-tuned encoder does text classification on 40 million tickets a day; the LLM reviews only the uncertain ones.
Origin
M. E. Maron's 'Automatic Indexing: An Experimental Inquiry' (1961) assigned documents to subject categories with a probabilistic classifier of the kind now called naive Bayes. Machine-learned text categorization became standard in the 1990s with benchmark collections such as Reuters-21578, and Bayesian spam filters popularized it from the late 1990s.
Related
- classificationclassification, n.: Sorting things into categories — spam or not spam, which animal is in a photo, which language a text is written in — by learning from examples that are already labeled.
- sentiment analysissentiment analysis, n.: Using software to judge the feelings or opinions expressed in text — whether a review, post or comment is positive, negative or neutral, and about what.
- bag of wordsbag of words, n.: A simple way of turning text into numbers by counting how often each word appears and ignoring word order — like describing a recipe only by its shopping list.
- TF-IDFTF-IDF, abbr.: A simple score for picking out the words that characterize a document: a word counts for more the more often it appears there, and for less the more of the collection's other documents also use it.
- naive Bayesnaive Bayes, n.: A simple, fast way of sorting items into categories using probabilities, which pretends that each clue is independent of the others. It is the classic technique behind early email spam filters.
- content moderationcontent moderation, n.: Checking what people post, or what an AI produces, and removing, limiting or labeling whatever breaks the rules or the law — done by people, by AI, or by both together.
- zero-shot learningzero-shot learning, n.: Doing a task without being shown a single example of it — say, an AI sorting reviews into positive and negative just from being told to, or recognizing an animal it never saw in training.
Sources
- Maron, M. E. (1961). Automatic Indexing: An Experimental Inquiry. Journal of the ACM 8(3), 404–417.
- Sebastiani, F. (2002). Machine Learning in Automated Text Categorization. ACM Computing Surveys 34(1), 1–47.
Mentioned in
natural language processingnatural language processing, n.: The field that teaches computers to handle human language — to read, interpret, translate, summarize and produce text and speech. It is one of the oldest and largest areas of artificial intelligence., bag of wordsbag of words, n.: A simple way of turning text into numbers by counting how often each word appears and ignoring word order — like describing a recipe only by its shopping list., naive Bayesnaive Bayes, n.: A simple, fast way of sorting items into categories using probabilities, which pretends that each clue is independent of the others. It is the classic technique behind early email spam filters., named-entity recognitionnamed-entity recognition, n.: Software that spots names and similar expressions in text and labels each by type: in 'Maria flew from Lagos to Paris on Monday', it marks a person, two cities and a date., sentiment analysissentiment analysis, n.: Using software to judge the feelings or opinions expressed in text — whether a review, post or comment is positive, negative or neutral, and about what., TF-IDFTF-IDF, abbr.: A simple score for picking out the words that characterize a document: a word counts for more the more often it appears there, and for less the more of the collection's other documents also use it., topic modeltopic model, n.: A method that reads a large pile of documents and discovers the themes running through them, describing each theme by its typical words and each document by its mix of themes., decision modeldecision model, n.: A kind of AI language model that reads text but answers only with numbers — a yes-or-no probability, a choice or a score — instead of writing words., language identificationlanguage identification, n.: Automatically working out which language a piece of text or speech is in — a basic sorting step when building multilingual AI training data from the web.