방법 비교

	Supervised Text Classification	Dictionary-Based Text Analysis in Politics
분야	Political Science	Political Science
계열	Process / pipeline	Process / pipeline
기원 연도	2013	2013
창시자	Machine-learning classification tradition (formalized for political text by Grimmer & Stewart; category-proportion variant by Hopkins & King)	Content-analysis tradition (formalized for political text by Grimmer & Stewart; sentiment dictionaries by Young & Soroka)
유형	Supervised machine-learning classification of documents	Rule-based text scoring from validated word lists
원전	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.	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.
별칭	Supervised document classification, Text categorization, Automated text coding, Supervised content analysis	Lexicon-based political text analysis, Dictionary methods for political texts, Word-count content analysis of political texts, Political keyword counting
관련	5	5
요약	Supervised text classification trains a statistical model on documents that humans have hand-labeled, then uses it to assign categories — topic, tone, position, relevance — to the much larger set of unlabeled documents. Unlike dictionary methods, which apply a fixed word list, a supervised classifier learns from examples which textual features predict each category, so it can capture context-dependent and non-obvious cues. Grimmer and Stewart present it as a core text-as-data workflow, and a key insight is that for many political-science questions the goal is not perfect document-by-document labels but accurate estimates of category proportions across a corpus.	Dictionary-based text analysis scores documents by counting how often they use words from a predefined, validated list — a dictionary or lexicon — tied to a concept such as sentiment, emotion, or a policy area. Each document's score is essentially the rate at which dictionary terms appear, so a corpus of speeches, news articles, or manifestos can be measured for tone or thematic emphasis quickly and transparently. It is the simplest and most interpretable family of automated content-analysis methods, and Grimmer and Stewart treat it as a baseline against which more elaborate text-as-data tools are judged.