Changes in version 0.1.4                        

  - New math_mode argument in prep_texts() keeps numbers, math
    operators, and symbols, and strips only sentence-end punctuation.
  - First CRAN release.

                        Changes in version 0.1.3                        

  - Updated semantic analysis and topic modeling functions.
  - Refreshed vignettes and pkgdown reference index.

                        Changes in version 0.1.0                        

  - Renamed fit_embedding_topics() to fit_embedding_model(). The old
    name is deprecated.
  - Multi-format file import (PDF, DOCX, XLSX, CSV, TXT).
  - Hybrid topic modeling (STM + BERTopic).
  - Semantic similarity and document clustering.
  - Lexical diversity metrics (TTR, MTLD).
  - Log-odds ratio analysis and lexical dispersion plots.
  - Neural sentiment analysis via transformers.
  - spaCy support for POS tagging, NER, lemmatization, and dependency
    parsing.
  - Sentence-transformer document embeddings.
  - LLM integration (OpenAI, Gemini) for topic labeling and RAG.

                        Changes in version 0.0.2                        

  - Documentation improvements.

                        Changes in version 0.0.1                        

  - First development release.
  - Text preprocessing, STM topic modeling, basic Shiny app.