Text Analysis

This LibGuide is designed to support students and researchers who are new to text analysis or looking to deepen their understanding of the field.

This guide is organized into key areas to support your learning and practice:

• Methods & Approaches in Text Analysis: An overview of common techniques used to analyze texts, including:
  • Term Frequency: Counting how often words appear to identify key terms.
  • Collocation Analysis: Studying word pairs or groups that frequently occur together.
  • Sentiment Analysis: Detecting the emotional tone behind the text.
  • Text Classification: Categorizing texts into predefined groups based on content.
  • Topic Modeling: Discovering underlying themes or topics within large text collections.
• Text Analysis Tools & Platforms: A look at popular tools to assist your analysis, including:
  • Web-based tools
  • Python packages and libraries
  • R packages and libraries
• Source Texts for Analysis: Sources for locating quality texts to practice and apply your analysis skills.
• Example Text Analysis Projects: Examples and ideas to inspire your own text analysis work and deepen your understanding.
• Responsible Text Analysis: Sources to examine important methodological and ethical considerations when working with textual data.

Text analysis is the process of exploring written texts to uncover new insights by applying computational techniques that detect patterns, trends, and connections across large sets of documents.

Text analysis can reveal patterns not easily discoverable by a single reader, for instance across thousands or millions of documents. However, it is always limited by the texts used and reflects the biases of the original content creators as well as the source selection.

Common applications of text analysis include summarizing texts, identifying key words and phrases that differentiate texts, and categorizing or grouping texts. Text analyses commonly rely on counting how often words appear in texts to make comparisons, but methods like natural language processing (NLP) can take the structure of language into account as well. 

The following Google Slides decks provide definitions, example workflows, method introductions, and examples of what text analysis is and how it can be used.