📂 Glossary of AI Terms

Glossary of AI Terms

Clear definitions for AI writing and text detection terms — perplexity, burstiness, LLMs, and more.

Active Voice Active voice is a sentence construction where the subject performs the action — producing more direct, energetic, and readable prose compared to passive voice.
AI Detector An AI detector is a tool that analyzes text to determine whether it was written by a human or generated by an artificial intelligence language model.
AI Humanizer An AI humanizer is a tool that rewrites AI-generated text to sound more natural and human-like, reducing the statistical signals that AI detectors use to identify machine-generated content.
Burstiness Burstiness measures variation in sentence length and complexity. Human writing tends to be more bursty than AI-generated text.
Canonicalization Canonicalization is the process of selecting the preferred URL for a piece of content when multiple URLs could return the same or very similar content — preventing duplicate content issues in search indexing.
Content Quality Content quality refers to how well a piece of writing serves its intended reader — covering accuracy, depth, clarity, originality, and relevance to the reader's actual need.
Context Window The context window is the maximum amount of text — measured in tokens — that a language model can process at one time, including both the input prompt and the generated output.
E-E-A-T E-E-A-T stands for Experience, Expertise, Authoritativeness, and Trustworthiness — Google's framework for evaluating the quality and credibility of web content, particularly important for health, finance, and other high-stakes topics.
False Positive Rate In AI detection, the false positive rate is the percentage of genuinely human-written texts that an AI detector incorrectly classifies as AI-generated.
Fine-Tuning Fine-tuning is the process of further training a pre-trained language model on a smaller, task-specific dataset to improve its performance on a particular type of task or domain.
GPTZero GPTZero is an AI text detection tool built by Edward Tian in 2023, widely used in academic settings to detect AI-generated submissions. It measures perplexity and burstiness to estimate AI probability.
Grammar Checker A grammar checker is a writing tool that automatically identifies and suggests corrections for grammatical errors, spelling mistakes, punctuation issues, and style problems in text.
Hallucination In AI, hallucination refers to the phenomenon where a language model generates factually incorrect information that sounds confident and plausible — making up citations, statistics, or facts that don't exist.
Keyword Density Keyword density is the percentage of times a target keyword appears in a piece of text relative to the total word count — a basic SEO metric that has become less important as search engines grew more sophisticated.
Knowledge Cutoff A knowledge cutoff is the date after which a language model has no information about world events, because its training data was collected before that point.
Large Language Model (LLM) A large language model is an AI system trained on massive text datasets to understand and generate human language. GPT-4, Claude, and Gemini are examples.
Meta Description A meta description is an HTML attribute that provides a short summary of a web page's content — displayed in search results below the page title and used to influence click-through rates.
Natural Language Processing (NLP) Natural language processing (NLP) is the field of computer science and linguistics concerned with enabling computers to understand, interpret, and generate human language.
Open Graph Open Graph is a protocol introduced by Facebook that allows web pages to control how their content appears when shared on social media platforms — defining the title, image, and description shown in link previews.
Originality.ai Originality.ai is an AI content detection and plagiarism checking tool designed primarily for content publishers, editors, and SEO agencies who need to verify that submitted content is human-written.
Paraphrasing Tool A paraphrasing tool is software that automatically rewrites text in different words while preserving the original meaning — ranging from simple synonym substitution to AI-powered structural rewriting.
Paraphrasing Paraphrasing is the restatement of someone else's ideas in your own words and sentence structure, typically accompanied by a citation to the original source.
Passive Voice Passive voice is a grammatical construction where the subject of a sentence receives the action rather than performing it — often associated with formal writing and AI-generated text.
Perplexity In AI text detection, perplexity measures how predictable a piece of text is to a language model. Lower perplexity often indicates AI-generated text.
Plagiarism Plagiarism is presenting someone else's words, ideas, or work as your own without proper attribution, regardless of whether the original was copied verbatim or paraphrased without credit.
Prompt Engineering Prompt engineering is the practice of crafting and optimizing text inputs to language models to consistently produce higher-quality, more accurate, or better-formatted outputs.
Prompt A prompt is the input text given to a language model that instructs it what to generate — including questions, instructions, examples, and context.
Flesch Reading Ease Score The Flesch Reading Ease score is a readability formula that measures how easy a piece of text is to read, based on average sentence length and average number of syllables per word.
Readability Readability refers to how easily a piece of text can be read and understood, typically measured by formulas based on sentence length and word complexity.
SEO Writing SEO writing is the practice of creating web content that is both useful to human readers and optimised for search engine ranking — balancing keyword relevance with genuine content quality.
Structured Data Structured data is standardised code added to web pages (typically as JSON-LD) that helps search engines understand page content and can enable rich results like FAQ dropdowns, star ratings, and breadcrumb trails in search results.
Text Summarization Text summarization is the process of producing a condensed version of a longer text that retains its key information, main arguments, and essential meaning.
Title Tag A title tag is the HTML element that specifies the title of a web page, displayed in browser tabs, search engine results, and social media previews — one of the most important on-page SEO elements.
Token In the context of large language models, a token is the basic unit of text that the model processes — roughly corresponding to a word, part of a word, or punctuation character.
Tone In writing, tone refers to the attitude, voice, and emotional register that a piece of writing conveys — from formal to casual, assertive to tentative, warm to detached.
Training Data Training data is the large collection of text (and other content) that a language model learns from during the training process, shaping the patterns, knowledge, and style of its outputs.
Transformer A transformer is the neural network architecture that underlies modern large language models, introduced in the 2017 paper "Attention Is All You Need" by Vaswani et al.
Word Count Word count is the total number of words in a piece of text — used as a basic measure of content length in writing, publishing, SEO, and academic contexts.