Сравнение методов

	Automated Content Analysis	Dictionary-Based Text Analysis
Область	Communication	Communication
Семейство	Process / pipeline	Process / pipeline
Год появления	2013	2003
Автор метода	Justin Grimmer & Brandon Stewart (synthesis)	Lexicon tradition (Pennebaker LIWC; General Inquirer)
Тип	Computational pipeline for measuring features of large text corpora	Word-count text measurement against predefined category dictionaries
Основополагающий источник	Grimmer, J., & Stewart, B. M. (2013). Text as data: The promise and pitfalls of automatic content analysis methods for political texts. Political Analysis, 21(3), 267–297.	Pennebaker, J. W., Mehl, M. R., & Niederhoffer, K. G. (2003). Psychological aspects of natural language use: Our words, our selves. Annual Review of Psychology, 54, 547–577.
Другие названия	Computational content analysis, Text-as-data analysis, Automated text analysis, Otomatik İçerik Analizi	Lexicon-based text analysis, Word-count text analysis, Dictionary method for content analysis, Sözlük Tabanlı Metin Analizi
Связанные	4	4
Сводка	Automated content analysis is the computational measurement of text features at a scale impossible by hand, using natural-language processing and machine learning to classify, scale, or discover the content of large corpora. Synthesized for the social sciences by Grimmer and Stewart's 2013 'Text as Data,' it spans supervised classification, unsupervised discovery, and scaling, all unified by the principle that automated methods augment but do not replace careful human judgment and validation.	Dictionary-based text analysis measures concepts in text by counting how often words belonging to predefined category lists — dictionaries — appear in each document. It is the workhorse lexicon method behind tools like LIWC and the General Inquirer, prized for its transparency and scalability: a category score is simply the share of a document's words that match the category's word list.